This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
I am trying to evaluate Object detection model performance on TI Edge AI. I have been getting some weird issues.
Kernel Died
Hi Akash, In the cloud, please check custom-model-tfl.ipynb as I think your notebook has the wrong "image_class_to_name" import. It should be "from scripts.utils". You can also inspect notebooks from TI's edgeai-tidl-tools in github
Also, below few more tips to debug issues:
- Does the model run on ARM only? You can check vcls-tfl-arm.ipynb if needed
- Did he got compilation logs? Any errors?. You can check custom-model-tfl.ipynb on how to add "loggerWritter" to your notebook. Currently, we are saving compilation docker's container logs in "notebooks/logs/"
- Also, we added a way to get EVM's console logs. Not always we get info there, but in case of errors, it might get some things printed there and worthy to check it. You can do that by running evm-console-log.ipynb
- Additionally, a good way to debug if subgraphs are created and are correct is by inspecting *.svg files inside notebooks/custom-artifacts/ folder (or /custom-artifacts-temp if you didn't copy them inside your workspace - last cell to run). *.svg files are inside "tempDir". Alternatively, we added subgraph visualization to our custom-model notebooks. You can copy that particular cell in your notebook as well.
thank you,
Paula
Hello Paula,
Thanks for the reply. I switched the notebook. I still have the kernel dying issue though. could you please help me to understand the issue? Please find the attached log.
tidl_tools_path = /opt/tidl_tools
artifacts_folder = ../custom-artifacts-temp/tflite/mobilenetv1
tidl_tensor_bits = 8
debug_level = 3
num_tidl_subgraphs = 16
tidl_denylist = 1 25
tidl_calibration_accuracy_level = 7
tidl_calibration_options:num_frames_calibration = 1
tidl_calibration_options:bias_calibration_iterations = 3
power_of_2_quantization = 2
enable_high_resolution_optimization = 0
pre_batchnorm_fold = 1
add_data_convert_ops = 0
output_feature_16bit_names_list =
m_params_16bit_names_list =
reserved_compile_constraints_flag = 1601
ti_internal_reserved_1 =
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/Conv/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/Conv/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/Conv/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_1/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_2/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_3/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_4/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_5/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_6/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_7/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_8/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_9/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_10/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_11/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_12/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_13/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_14/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 5 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_15/add_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/expand/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/expand/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/expand/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 4 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/depthwise/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/depthwise/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/depthwise/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/project/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/expanded_conv_16/project/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/Conv_1/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/Conv_1/BatchNorm/FusedBatchNorm_original
Unsupported (import) TIDL layer type for Tflite layer type --- 21 layer output name--- FeatureExtractor/MobilenetV2/Conv_1/Relu6_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_2_1x1_256/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_2_1x1_256/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_2_1x1_256/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_2_3x3_s2_512/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_2_3x3_s2_512/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_2_3x3_s2_512/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_3_1x1_128/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_3_1x1_128/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_3_1x1_128/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_3_3x3_s2_256/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_3_3x3_s2_256/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_3_3x3_s2_256/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_4_1x1_128/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_4_1x1_128/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_4_1x1_128/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_4_3x3_s2_256/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_4_3x3_s2_256/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_4_3x3_s2_256/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_5_1x1_64/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_5_1x1_64/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_1_Conv2d_5_1x1_64/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_5_3x3_s2_128/BatchNorm/FusedBatchNorm/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_5_3x3_s2_128/BatchNorm/FusedBatchNorm_original
Supported TIDL layer type --- 3 Tflite layer type --- 19 layer output name--- FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_5_3x3_s2_128/Relu_original
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_0/BoxEncodingPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_0/BoxEncodingPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_0/Reshape
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_0/ClassPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_0/ClassPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_0/Reshape_1
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_1/BoxEncodingPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_1/BoxEncodingPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_1/Reshape
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_1/ClassPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_1/ClassPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_1/Reshape_1
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_2/BoxEncodingPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_2/BoxEncodingPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_2/Reshape
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_2/ClassPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_2/ClassPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_2/Reshape_1
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_3/BoxEncodingPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_3/BoxEncodingPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_3/Reshape
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_3/ClassPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_3/ClassPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_3/Reshape_1
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_4/BoxEncodingPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_4/BoxEncodingPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_4/Reshape
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_4/ClassPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_4/ClassPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_4/Reshape_1
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_5/BoxEncodingPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_5/BoxEncodingPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_5/Reshape
Supported TIDL layer type --- 1 Tflite layer type --- 3 layer output name--- BoxPredictor_5/ClassPredictor/BiasAdd/conv_original
Supported TIDL layer type --- 8 Tflite layer type --- 0 layer output name--- BoxPredictor_5/ClassPredictor/BiasAdd_original
Unsupported (TIDL check) TIDL layer type --- 39 Tflite layer type --- 22 layer output name--- BoxPredictor_5/Reshape_1
Supported TIDL layer type --- 12 Tflite layer type --- 2 layer output name--- concat
Warning : concat requires 4D input tensors - only 3 dims present.. Ignore if object detection network
Unsupported (TIDL check) TIDL layer type --- 12 Tflite layer type --- 2 layer output name--- concat_1
Number of subgraphs:48 , 163 nodes delegated out of 211 nodes
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/Conv/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_1/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_1/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_2/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_2/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_3/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_3/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_4/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_4/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_5/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_5/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_6/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_6/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_7/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_7/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_8/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_8/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_9/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_9/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_10/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_10/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_11/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_11/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_12/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_12/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_13/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_13/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_14/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_14/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_15/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_15/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_16/expand/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/expanded_conv_16/depthwise/Relu6_original
Layer type not supported by TIDL ---- tflite layer code - 21, tensor name - FeatureExtractor/MobilenetV2/Conv_1/Relu6_original
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
TIDL ALLOWLISTING LAYER CHECK -- [TIDL_ReshapeLayer] Only N th dimension can be non-zero, first N-1 dimension must be 1, only flatten reshape layer supported.
In TIDL_tfliteRtImportInit subgraph_id=86
Layer 0, subgraph id 86, name=FeatureExtractor/MobilenetV2/Conv/BatchNorm/FusedBatchNorm_original
Layer 1, subgraph id 86, name=Preprocessor/sub
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 3
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_runtimesOptimizeNet: LayerIndex = 4, dataIndex = 3
************** Frame index 1 : Running float import *************
In TIDL_runtimesPostProcessNet
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************ in TIDL_subgraphRtCreate ************
0.0s: VX_ZONE_INIT:Enabled
0.5s: VX_ZONE_ERROR:Enabled
0.6s: VX_ZONE_WARNING:Enabled
0.585s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
TIDL_initDebugTraceParams Done
Alg Alloc for Layer # - 0
Alg Alloc for Layer # - 1
Alg Alloc for Layer # - 2
Alg Alloc for Layer # - 3
TIDL Memory requiement
MemRecNum , Space , Attribute , SizeinBytes
0 , DDR , Persistent, 15208
1 , DDR , Persistent, 136
2 , DDR , Scratch , 16384
3 , DDR , Scratch , 4096
4 , DDR , Scratch , 57344
5 , DDR , Persistent, 1664
6 , DDR , Scratch , 3142528
7 , DDR , Scratch , 256
8 , DDR , Scratch , 46080128
9 , DDR , Scratch , 23043072
10 , DDR , Persistent, 5431680
11 , DDR , Persistent, 153856
12 , DDR , Scratch , 256
13 , DDR , Persistent, 128
NOTE: Memory requirement in host emulation can be different from the same on EVM
To get the actual TIDL memory requirement make sure to run on EVM with
writeTraceLevel = 0
Alg Init for Layer # - 0 out of 3
Alg Init for Layer # - 1 out of 3
Alg Init for Layer # - 2 out of 3
Alg Init for Layer # - 3 out of 3
************ TIDL_subgraphRtCreate done ************
In TIDL_tfliteRtImportInit subgraph_id=98
Layer 0, subgraph id 98, name=FeatureExtractor/MobilenetV2/expanded_conv/depthwise/BatchNorm/FusedBatchNorm_original
Layer 1, subgraph id 98, name=FeatureExtractor/MobilenetV2/Conv/Relu6_original
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 4
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_runtimesOptimizeNet: LayerIndex = 4, dataIndex = 3
************** Frame index 1 : Running float import *************
In TIDL_runtimesPostProcessNet
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************ in TIDL_subgraphRtCreate ************
TIDL_initDebugTraceParams Done
Alg Alloc for Layer # - 0
Alg Alloc for Layer # - 1
Alg Alloc for Layer # - 2
Alg Alloc for Layer # - 3
TIDL Memory requiement
MemRecNum , Space , Attribute , SizeinBytes
0 , DDR , Persistent, 15208
1 , DDR , Persistent, 136
2 , DDR , Scratch , 16384
3 , DDR , Scratch , 4096
4 , DDR , Scratch , 57344
5 , DDR , Persistent, 1664
6 , DDR , Scratch , 3142528
7 , DDR , Scratch , 256
8 , DDR , Scratch , 46080128
9 , DDR , Scratch , 23660544
10 , DDR , Persistent, 5431680
11 , DDR , Persistent, 153856
12 , DDR , Scratch , 256
13 , DDR , Persistent, 128
NOTE: Memory requirement in host emulation can be different from the same on EVM
To get the actual TIDL memory requirement make sure to run on EVM with
writeTraceLevel = 0
Alg Init for Layer # - 0 out of 3
Alg Init for Layer # - 1 out of 3
Alg Init for Layer # - 2 out of 3
Alg Init for Layer # - 3 out of 3
************ TIDL_subgraphRtCreate done ************
In TIDL_tfliteRtImportInit subgraph_id=115
Layer 0, subgraph id 115, name=FeatureExtractor/MobilenetV2/expanded_conv_1/expand/BatchNorm/FusedBatchNorm_original
Layer 1, subgraph id 115, name=FeatureExtractor/MobilenetV2/expanded_conv/depthwise/Relu6_original
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 3
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 3
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_runtimesOptimizeNet: LayerIndex = 6, dataIndex = 5
************** Frame index 1 : Running float import *************
In TIDL_runtimesPostProcessNet
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************ in TIDL_subgraphRtCreate ************
TIDL_initDebugTraceParams Done
Alg Alloc for Layer # - 0
Alg Alloc for Layer # - 1
Alg Alloc for Layer # - 2
Alg Alloc for Layer # - 3
Alg Alloc for Layer # - 4
Alg Alloc for Layer # - 5
TIDL Memory requiement
MemRecNum , Space , Attribute , SizeinBytes
0 , DDR , Persistent, 15208
1 , DDR , Persistent, 136
2 , DDR , Scratch , 16384
3 , DDR , Scratch , 4096
4 , DDR , Scratch , 57344
5 , DDR , Persistent, 3648
6 , DDR , Scratch , 12044928
7 , DDR , Scratch , 256
8 , DDR , Scratch , 138240128
9 , DDR , Scratch , 69123072
10 , DDR , Persistent, 5431680
11 , DDR , Persistent, 172416
12 , DDR , Scratch , 256
13 , DDR , Persistent, 128
NOTE: Memory requirement in host emulation can be different from the same on EVM
To get the actual TIDL memory requirement make sure to run on EVM with
writeTraceLevel = 0
Alg Init for Layer # - 0 out of 5
Alg Init for Layer # - 1 out of 5
Alg Init for Layer # - 2 out of 5
Alg Init for Layer # - 3 out of 5
Alg Init for Layer # - 4 out of 5
Alg Init for Layer # - 5 out of 5
************ TIDL_subgraphRtCreate done ************
In TIDL_tfliteRtImportInit subgraph_id=109
Layer 0, subgraph id 109, name=FeatureExtractor/MobilenetV2/expanded_conv_1/depthwise/BatchNorm/FusedBatchNorm_original
Layer 1, subgraph id 109, name=FeatureExtractor/MobilenetV2/expanded_conv_1/expand/Relu6_original
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 4
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_runtimesOptimizeNet: LayerIndex = 4, dataIndex = 3
************** Frame index 1 : Running float import *************
In TIDL_runtimesPostProcessNet
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************ in TIDL_subgraphRtCreate ************
TIDL_initDebugTraceParams Done
Alg Alloc for Layer # - 0
Alg Alloc for Layer # - 1
Alg Alloc for Layer # - 2
Alg Alloc for Layer # - 3
TIDL Memory requiement
MemRecNum , Space , Attribute , SizeinBytes
0 , DDR , Persistent, 15208
1 , DDR , Persistent, 136
2 , DDR , Scratch , 16384
3 , DDR , Scratch , 4096
4 , DDR , Scratch , 57344
5 , DDR , Persistent, 2432
6 , DDR , Scratch , 2422528
7 , DDR , Scratch , 256
8 , DDR , Scratch , 34560128
9 , DDR , Scratch , 70975488
10 , DDR , Persistent, 5431680
11 , DDR , Persistent, 153856
12 , DDR , Scratch , 256
13 , DDR , Persistent, 128
NOTE: Memory requirement in host emulation can be different from the same on EVM
To get the actual TIDL memory requirement make sure to run on EVM with
writeTraceLevel = 0
Alg Init for Layer # - 0 out of 3
Alg Init for Layer # - 1 out of 3
Alg Init for Layer # - 2 out of 3
Alg Init for Layer # - 3 out of 3
************ TIDL_subgraphRtCreate done ************
In TIDL_tfliteRtImportInit subgraph_id=256
Layer 0, subgraph id 256, name=FeatureExtractor/MobilenetV2/expanded_conv_1/project/BatchNorm/FusedBatchNorm_original
Layer 1, subgraph id 256, name=FeatureExtractor/MobilenetV2/expanded_conv_2/expand/BatchNorm/FusedBatchNorm_original
Layer 2, subgraph id 256, name=FeatureExtractor/MobilenetV2/expanded_conv_1/depthwise/Relu6_original
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 3
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 3
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_runtimesOptimizeNet: LayerIndex = 7, dataIndex = 5
************** Frame index 1 : Running float import *************
In TIDL_runtimesPostProcessNet
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************ in TIDL_subgraphRtCreate ************
TIDL_initDebugTraceParams Done
Alg Alloc for Layer # - 0
Alg Alloc for Layer # - 1
Alg Alloc for Layer # - 2
Alg Alloc for Layer # - 3
Alg Alloc for Layer # - 4
Alg Alloc for Layer # - 5
Alg Alloc for Layer # - 6
TIDL Memory requiement
MemRecNum , Space , Attribute , SizeinBytes
0 , DDR , Persistent, 15208
1 , DDR , Persistent, 136
2 , DDR , Scratch , 16384
3 , DDR , Scratch , 4096
4 , DDR , Scratch , 57344
5 , DDR , Persistent, 4320
6 , DDR , Scratch , 4304800
7 , DDR , Scratch , 256
8 , DDR , Scratch , 51840128
9 , DDR , Scratch , 25923072
10 , DDR , Persistent, 5431680
11 , DDR , Persistent, 172416
12 , DDR , Scratch , 256
13 , DDR , Persistent, 128
NOTE: Memory requirement in host emulation can be different from the same on EVM
To get the actual TIDL memory requirement make sure to run on EVM with
writeTraceLevel = 0
Alg Init for Layer # - 0 out of 6
Alg Init for Layer # - 1 out of 6
Alg Init for Layer # - 2 out of 6
Alg Init for Layer # - 3 out of 6
Alg Init for Layer # - 4 out of 6
Alg Init for Layer # - 5 out of 6
Alg Init for Layer # - 6 out of 6
************ TIDL_subgraphRtCreate done ************
In TIDL_tfliteRtImportInit subgraph_id=250
Layer 0, subgraph id 250, name=FeatureExtractor/MobilenetV2/expanded_conv_2/depthwise/BatchNorm/FusedBatchNorm_original
Layer 1, subgraph id 250, name=FeatureExtractor/MobilenetV2/expanded_conv_2/expand/Relu6_original
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 4
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_runtimesOptimizeNet: LayerIndex = 4, dataIndex = 3
************** Frame index 1 : Running float import *************
In TIDL_runtimesPostProcessNet
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************ in TIDL_subgraphRtCreate ************
TIDL_initDebugTraceParams Done
Alg Alloc for Layer # - 0
Alg Alloc for Layer # - 1
Alg Alloc for Layer # - 2
Alg Alloc for Layer # - 3
TIDL Memory requiement
MemRecNum , Space , Attribute , SizeinBytes
0 , DDR , Persistent, 15208
1 , DDR , Persistent, 136
2 , DDR , Scratch , 16384
3 , DDR , Scratch , 4096
4 , DDR , Scratch , 57344
5 , DDR , Persistent, 3008
6 , DDR , Scratch , 3502528
7 , DDR , Scratch , 256
8 , DDR , Scratch , 51840128
9 , DDR , Scratch , 27319296
10 , DDR , Persistent, 5431680
11 , DDR , Persistent, 153856
12 , DDR , Scratch , 256
13 , DDR , Persistent, 128
NOTE: Memory requirement in host emulation can be different from the same on EVM
To get the actual TIDL memory requirement make sure to run on EVM with
writeTraceLevel = 0
Alg Init for Layer # - 0 out of 3
Alg Init for Layer # - 1 out of 3
Alg Init for Layer # - 2 out of 3
Alg Init for Layer # - 3 out of 3
************ TIDL_subgraphRtCreate done ************
In TIDL_tfliteRtImportInit subgraph_id=273
Layer 0, subgraph id 273, name=FeatureExtractor/MobilenetV2/expanded_conv_3/expand/BatchNorm/FusedBatchNorm_original
Layer 1, subgraph id 273, name=FeatureExtractor/MobilenetV2/expanded_conv_1/project/BatchNorm/FusedBatchNorm_original
Layer 2, subgraph id 273, name=FeatureExtractor/MobilenetV2/expanded_conv_2/depthwise/Relu6_original
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 3
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_tfliteRtImportNode TIDL Layer type 5 Tflite builtin code type 0
In TIDL_tfliteRtImportNode TIDL Layer type 1 Tflite builtin code type 3
In TIDL_tfliteRtImportNode TIDL Layer type 8 Tflite builtin code type 0
In TIDL_runtimesOptimizeNet: LayerIndex = 8, dataIndex = 7
************** Frame index 1 : Running float import *************
In TIDL_runtimesPostProcessNet
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************ in TIDL
Akash, sorry for the delay. I was wondering if you can also compile this model using our github edgeai-tidl-tools
The reason is above log is not completed (probably because the kernel died).
Alternatively, if you can share this model with us we can test it.
There is a potential issue with TFLite and Relu6. But we would like to confirm.
thank you,
Paula
Our's is a custom tflite model. I am trying to compile the model using the mentioned repo but I am not able to. I tried using this script python3 tflrt_delegate.py -c with my model. But getting errors that the "frozen inference graph is not available in config". Could you please provide me an example of how to do this?
Hi Akash, first at all I want to confirm. You were able to run ./run_python_examples.sh?
If so, for adding a model in TFLite python script there are two main files to check
In tflrt_delegate.py There is a list of models to run: https://github.com/TexasInstruments/edgeai-tidl-tools/blob/c6987ebeb67e48323a1e9e62f855d35c9da9d5d5/examples/osrt_python/tfl/tflrt_delegate.py#L213 you can add your model name there.
In common_utils.py you can add your model following one of the examples in models_configs
Notes:
Let me know if you face any issues running your model in edgeai-tidl-tools with python scripts
thank you,
Paula
Hello Paula,
Yes, I was able to run run_python_examples.sh. Please find the attached. I did the changes as you mentioned. When I ran the script again with my custom model it threw some warnings and then it stuck. Please find the log. Some files are generated in the model-artifacts directory for my custom model.
ripts/run_python_examples.sh
X64 Architecture
Running 3 Models - ['cl-tfl-mobilenet_v1_1.0_224', 'ss-tfl-deeplabv3_mnv2_ade20k_float', 'od-tfl-ssd_mobilenet_v2_300_float']
Running_Model : cl-tfl-mobilenet_v1_1.0_224
Running_Model : ss-tfl-deeplabv3_mnv2_ade20k_float
Running_Model : od-tfl-ssd_mobilenet_v2_300_float
TIDL Meta PipeLine (Proto) File :
Number of OD backbone nodes = 0
Size of odBackboneNodeIds = 0
Number of subgraphs:1 , 81 nodes delegated out of 81 nodes
Number of subgraphs:1 , 34 nodes delegated out of 34 nodes
Warning : concat requires 4D input tensors - only 3 dims present.. Ignore if object detection network
Number of subgraphs:1 , 107 nodes delegated out of 107 nodes
Warning : concat requires 4D input tensors - only 3 dims present.. Ignore if object detection network
WARNING: Batch Norm Layer scale_logits's coeff cannot be found(or not match) in coef file, Random bias will be generated! Only for evaluation usage! Results are all random!
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
************** Frame index 1 : Running float import *************
************** Frame index 1 : Running float import *************
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.8s: VX_ZONE_ERROR:Enabled
0.10s: VX_ZONE_WARNING:Enabled
0.711s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear_TIDL_0 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear_TIDL_1 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] decoder/ResizeBilinear Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear_1 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 6 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.11s: VX_ZONE_ERROR:Enabled
0.12s: VX_ZONE_WARNING:Enabled
0.402s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.9s: VX_ZONE_ERROR:Enabled
0.10s: VX_ZONE_WARNING:Enabled
0.339s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
************ Frame index 1 : Running float inference ****************
************ Frame index 2 : Running fixed point mode for calibration ****************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-tfl-mobilenet_v1_1.0_224/tempDir/86_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 474.26 .... ..... ... .... .....
# 1 . ..
************ Frame index 1 : Running float inference ****************
T 487.03 .... ..... ... .... .....
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-tfl-mobilenet_v1_1.0_224/tempDir/86_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 532.76 .... ..... ... .... .....
# 1 . ..
************ Frame index 2 : Running fixed point mode for calibration ****************
T 527.97 .... ..... ... .... .....
***************** Calibration iteration number 0 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-tfl-ssd_mobilenet_v2_300_float/tempDir/264_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-tfl-mobilenet_v1_1.0_224/tempDir/86_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 541.12 .... ..... ... .... .....
# 1 . .. T 542.12 .... ..... ... .... .....
***************** Calibration iteration number 1 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-tfl-mobilenet_v1_1.0_224/tempDir/86_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 1580.68 .... ..... ... .... .....
# 1 . .. T 564.05 .... ..... ... .... .....
# 1 . .. T 542.60 .... ..... ... .... .....
***************** Calibration iteration number 2 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-tfl-mobilenet_v1_1.0_224/tempDir/86_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..
************ Frame index 1 : Running float inference ****************
T 535.30 .... ..... ... .... .....
# 1 . .. T 1570.61 .... ..... ... .... ..... T 546.83 .... ..... ... .... .....
***************** Calibration iteration number 3 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-tfl-ssd_mobilenet_v2_300_float/tempDir/264_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-tfl-mobilenet_v1_1.0_224/tempDir/86_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 523.36 .... ..... ... .... .....
# 1 . .. T 1016.06 .... ..... ... .... .....
# 1 . .. T 533.75 .... ..... ... .... .....
***************** Calibration iteration number 4 completed ************************
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
substitute string tidl_net_ not found
****************************************************
** ALL MODEL CHECK PASSED **
****************************************************
Completed_Model : 1, Name : cl-tfl-mobilenet_v1_1.0_224 , Total time : 4194.30, Offload Time : 0.00 , DDR RW MBs : 0.00, Output File : py_out_cl-tfl-mobilenet_v1_1.0_224_ADE_val_00001801.jpg
T 1013.09 .... ..... ... .... .....
***************** Calibration iteration number 0 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-tfl-ssd_mobilenet_v2_300_float/tempDir/264_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 1048.71 .... ..... ... .... .....
# 1 . .. T 1066.50 .... ..... ... .... .....
***************** Calibration iteration number 1 completed ************************
************ Frame index 2 : Running fixed point mode for calibration ****************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-tfl-deeplabv3_mnv2_ade20k_float/tempDir/201_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-tfl-ssd_mobilenet_v2_300_float/tempDir/264_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 978.42 .... ..... ... .... .....
# 1 . .. T 973.17 .... ..... ... .... .....
***************** Calibration iteration number 2 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-tfl-ssd_mobilenet_v2_300_float/tempDir/264_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 1033.09 .... ..... ... .... .....
# 1 . .. T 1030.79 .... ..... ... .... .....
***************** Calibration iteration number 3 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-tfl-ssd_mobilenet_v2_300_float/tempDir/264_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 994.04 .... ..... ... .... .....
# 1 . .. T 999.78 .... ..... ... .... .....
***************** Calibration iteration number 4 completed ************************
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
substitute string tidl_net_ not found
****************************************************
** ALL MODEL CHECK PASSED **
****************************************************
Completed_Model : 3, Name : od-tfl-ssd_mobilenet_v2_300_float , Total time : 9786.46, Offload Time : 0.00 , DDR RW MBs : 0.00, Output File : py_out_od-tfl-ssd_mobilenet_v2_300_float_ADE_val_00001801.jpg
T 13495.86 .... ..... ... .... .....
# 1 . .. T 13470.31 .... ..... ... .... .....
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-tfl-deeplabv3_mnv2_ade20k_float/tempDir/201_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 5208.85 .... ..... ... .... .....
# 1 . .. T 5150.42 .... ..... ... .... .....
***************** Calibration iteration number 0 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-tfl-deeplabv3_mnv2_ade20k_float/tempDir/201_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 5122.47 .... ..... ... .... .....
# 1 . .. T 5094.49 .... ..... ... .... .....
***************** Calibration iteration number 1 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-tfl-deeplabv3_mnv2_ade20k_float/tempDir/201_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 5222.35 .... ..... ... .... .....
# 1 . .. T 5327.63 .... ..... ... .... .....
***************** Calibration iteration number 2 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-tfl-deeplabv3_mnv2_ade20k_float/tempDir/201_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 5413.74 .... ..... ... .... .....
# 1 . .. T 5375.34 .... ..... ... .... .....
***************** Calibration iteration number 3 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-tfl-deeplabv3_mnv2_ade20k_float/tempDir/201_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 5397.48 .... ..... ... .... .....
# 1 . .. T 5233.48 .... ..... ... .... .....
***************** Calibration iteration number 4 completed ************************
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
substitute string tidl_net_ not found
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear_TIDL_0 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear_TIDL_1 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] decoder/ResizeBilinear Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] ResizeBilinear_1 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
****************************************************
** 5 WARNINGS 0 ERRORS **
****************************************************
Completed_Model : 2, Name : ss-tfl-deeplabv3_mnv2_ade20k_float , Total time : 46160.62, Offload Time : 0.00 , DDR RW MBs : 0.00, Output File : py_out_ss-tfl-deeplabv3_mnv2_ade20k_float_ADE_val_00001801.jpg
Running 3 Models - ['cl-tfl-mobilenet_v1_1.0_224', 'ss-tfl-deeplabv3_mnv2_ade20k_float', 'od-tfl-ssd_mobilenet_v2_300_float']
Running_Model : cl-tfl-mobilenet_v1_1.0_224
Running_Model : ss-tfl-deeplabv3_mnv2_ade20k_float
Running_Model : od-tfl-ssd_mobilenet_v2_300_float
Number of subgraphs:1 , 34 nodes delegated out of 34 nodes
Number of subgraphs:1 , 81 nodes delegated out of 81 nodes
Number of subgraphs:1 , 107 nodes delegated out of 107 nodes
0.0s: VX_ZONE_INIT:Enabled
0.9s: VX_ZONE_ERROR:Enabled
0.10s: VX_ZONE_WARNING:Enabled
0.0s: VX_ZONE_INIT:Enabled
0.27s: VX_ZONE_ERROR:Enabled
0.28s: VX_ZONE_WARNING:Enabled
0.346s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
0.365s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
0.0s: VX_ZONE_INIT:Enabled
0.12s: VX_ZONE_ERROR:Enabled
0.13s: VX_ZONE_WARNING:Enabled
0.401s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
, 0 0.511485 missile ,, 1 0.262215 warplane, military plane ,, 2 0.187196 projectile, missile ,, 3 0.025072 cannon ,, 4 0.007760 submarine, pigboat, sub, U-boat ,
Saving image to ../../../output_images/
Completed_Model : 1, Name : cl-tfl-mobilenet_v1_1.0_224 , Total time : 118.93, Offload Time : 118.93 , DDR RW MBs : 0.00, Output File : py_out_cl-tfl-mobilenet_v1_1.0_224_airshow.jpg
Saving image to ../../../output_images/
Completed_Model : 3, Name : od-tfl-ssd_mobilenet_v2_300_float , Total time : 313.00, Offload Time : 312.99 , DDR RW MBs : 0.00, Output File : py_out_od-tfl-ssd_mobilenet_v2_300_float_image1.png
Saving image to ../../../output_images/
Completed_Model : 2, Name : ss-tfl-deeplabv3_mnv2_ade20k_float , Total time : 1292.48, Offload Time : 1292.47 , DDR RW MBs : 0.00, Output File : py_out_ss-tfl-deeplabv3_mnv2_ade20k_float_ADE_val_00001801.jpg
Available execution providers : ['TIDLExecutionProvider', 'TIDLCompilationProvider', 'CPUExecutionProvider']
Running 4 Models - ['cl-ort-resnet18-v1', 'cl-ort-caffe_squeezenet_v1_1', 'ss-ort-deeplabv3lite_mobilenetv2', 'od-ort-ssd-lite_mobilenetv2_fpn']
Running_Model : cl-ort-resnet18-v1
Downloading ../../../models/public/resnet18_opset9.onnx
Running_Model : cl-ort-caffe_squeezenet_v1_1
Downloading ../../../models/public/caffe_squeezenet_v1_1.prototxt
Running_Model : ss-ort-deeplabv3lite_mobilenetv2
Downloading ../../../models/public/deeplabv3lite_mobilenetv2.onnx
Running_Model : od-ort-ssd-lite_mobilenetv2_fpn
Downloading ../../../models/public/ssd-lite_mobilenetv2_fpn.onnx
Downloading ../../../models/public/caffe_squeezenet_v1_1.caffemodel
Converted model is valid!
Preliminary subgraphs created = 1
Final number of subgraphs created are : 1, - Offloaded Nodes - 124, Total Nodes - 124
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
************** Frame index 1 : Running float import *************
INFORMATION: [TIDL_ResizeLayer] 571 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] 576 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 3 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.6s: VX_ZONE_ERROR:Enabled
0.7s: VX_ZONE_WARNING:Enabled
0.332s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
caffemodel was successfully loaded
add model input information
add model output information and model intermediate output information
*.onnx model conversion completed
removing not constant initializers from model
frozen graph has been created
Converted model is valid!
Downloading ../../../models/public/ssd-lite_mobilenetv2_fpn.prototxt
the model has been successfully saved to ../../../models/public/caffe_squeezenet_v1_1.onnx
TIDL Meta PipeLine (Proto) File : ../../../models/public/ssd-lite_mobilenetv2_fpn.prototxt
ssd
Number of OD backbone nodes = 159
Size of odBackboneNodeIds = 159
Preliminary subgraphs created = 1
Final number of subgraphs created are : 1, - Offloaded Nodes - 494, Total Nodes - 494
********** Frame Index 1 : Running float inference **********
Converted model is valid!
Preliminary subgraphs created = 1
Final number of subgraphs created are : 1, - Offloaded Nodes - 68, Total Nodes - 68
TIDL Meta PipeLine (Proto) File : ../../../models/public/ssd-lite_mobilenetv2_fpn.prototxt
ssd
Warning :: img_w & img_h or img_size is not provided as part of prior_box_param, hence using img_w = 512 and img_h = 512 in prior box decoding
Warning :: img_w & img_h or img_size is not provided as part of prior_box_param, hence using img_w = 512 and img_h = 512 in prior box decoding
Warning :: img_w & img_h or img_size is not provided as part of prior_box_param, hence using img_w = 512 and img_h = 512 in prior box decoding
Warning :: img_w & img_h or img_size is not provided as part of prior_box_param, hence using img_w = 512 and img_h = 512 in prior box decoding
Warning :: img_w & img_h or img_size is not provided as part of prior_box_param, hence using img_w = 512 and img_h = 512 in prior box decoding
Warning :: img_w & img_h or img_size is not provided as part of prior_box_param, hence using img_w = 512 and img_h = 512 in prior box decoding
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.8s: VX_ZONE_ERROR:Enabled
0.9s: VX_ZONE_WARNING:Enabled
0.439s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
Warning : Requested Output Data Convert Layer is not Added to the network, It is currently not Optimal
************** Frame index 1 : Running float import *************
INFORMATION: [TIDL_ResizeLayer] Resize_153 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] Resize_156 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 3 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.9s: VX_ZONE_ERROR:Enabled
0.10s: VX_ZONE_WARNING:Enabled
0.356s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
********** Frame Index 1 : Running float inference **********
********** Frame Index 2 : Running fixed point mode for calibration **********
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-ort-deeplabv3lite_mobilenetv2/tempDir/566TIDL_cast_out_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..
********** Frame Index 2 : Running fixed point mode for calibration **********
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-caffe_squeezenet_v1_1/tempDir/prob_Y_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 305.59 .... ..... ... .... .....
# 1 . .. T 301.56 .... ..... ... .... .....
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-caffe_squeezenet_v1_1/tempDir/prob_Y_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 238.00 .... ..... ... .... .....
# 1 . .. T 229.80 .... ..... ... .... .....
***************** Calibration iteration number 0 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-caffe_squeezenet_v1_1/tempDir/prob_Y_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 226.05 .... ..... ... .... .....
# 1 . ..
********** Frame Index 1 : Running float inference **********
T 219.20 .... ..... ... .... .....
***************** Calibration iteration number 1 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-caffe_squeezenet_v1_1/tempDir/prob_Y_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 238.23 .... ..... ... .... .....
# 1 . .. T 238.13 .... ..... ... .... .....
***************** Calibration iteration number 2 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-caffe_squeezenet_v1_1/tempDir/prob_Y_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 234.60 .... ..... ... .... .....
# 1 . .. T 229.31 .... ..... ... .... .....
***************** Calibration iteration number 3 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-caffe_squeezenet_v1_1/tempDir/prob_Y_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 239.89 .... ..... ... .... .....
# 1 . .. T 229.35 .... ..... ... .... .....
***************** Calibration iteration number 4 completed ************************
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
substitute string tidl_net_ not found
****************************************************
** ALL MODEL CHECK PASSED **
****************************************************
Completed_Model : 2, Name : cl-ort-caffe_squeezenet_v1_1 , Total time : 2335.22, Offload Time : 294.18 , DDR RW MBs : 0, Output File : py_out_cl-ort-caffe_squeezenet_v1_1_ADE_val_00001801.jpg
T 3567.88 .... ..... ... .... .....
# 1 . ..
********** Frame Index 2 : Running fixed point mode for calibration **********
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-ort-ssd-lite_mobilenetv2_fpn/tempDir/boxeslabels_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 2123.56 .... ..... ... .... .....
# 1 . .. T 3377.50 .... ..... ... .... .....
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-ort-deeplabv3lite_mobilenetv2/tempDir/566TIDL_cast_out_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 2027.05 .... ..... ... .... .....
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-ort-ssd-lite_mobilenetv2_fpn/tempDir/boxeslabels_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 2380.03 .... ..... ... .... .....
# 1 . .. T 3738.21 .... ..... ... .... .....
# 1 . .. T 2354.68 .... ..... ... .... .....
***************** Calibration iteration number 0 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-ort-ssd-lite_mobilenetv2_fpn/tempDir/boxeslabels_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..Converted model is valid!
2022-04-21 11:43:00.620251230 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622074544 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622080860 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622086837 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622091961 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622097094 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622102482 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622107747 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622112605 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622117714 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622123029 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622128619 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622133902 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622138755 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622143400 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622148206 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622153084 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622158765 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622163559 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:00.622169038 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
Preliminary subgraphs created = 1
Final number of subgraphs created are : 1, - Offloaded Nodes - 52, Total Nodes - 52
T 3791.61 .... ..... ... .... .....
***************** Calibration iteration number 0 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-ort-deeplabv3lite_mobilenetv2/tempDir/566TIDL_cast_out_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.6s: VX_ZONE_ERROR:Enabled
0.8s: VX_ZONE_WARNING:Enabled
0.311s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
T 2514.11 .... ..... ... .... .....
# 1 . ..
********** Frame Index 1 : Running float inference **********
T 2400.66 .... ..... ... .... .....
***************** Calibration iteration number 1 completed ************************
********** Frame Index 2 : Running fixed point mode for calibration **********
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-resnet18-v1/tempDir/191_tidl_io_.qunat_stats_config.txt
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-ort-ssd-lite_mobilenetv2_fpn/tempDir/boxeslabels_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. ----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 4000.78 .... ..... ... .... .....
# 1 . .. T 1182.22 .... ..... ... .... .....
# 1 . .. T 1178.04 .... ..... ... .... ..... T 2375.80 .... ..... ... .... .....
# 1 . ..
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-resnet18-v1/tempDir/191_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 641.08 .... ..... ... .... .....
# 1 . .. T 637.81 .... ..... ... .... .....
***************** Calibration iteration number 0 completed ************************
T 3956.45 .... ..... ... .... .....
***************** Calibration iteration number 1 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-resnet18-v1/tempDir/191_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . ..
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-ort-deeplabv3lite_mobilenetv2/tempDir/566TIDL_cast_out_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 2426.68 .... ..... ... .... .....
***************** Calibration iteration number 2 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-ort-ssd-lite_mobilenetv2_fpn/tempDir/boxeslabels_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 648.55 .... ..... ... .... .....
# 1 . .. T 648.96 .... ..... ... .... .....
***************** Calibration iteration number 1 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-resnet18-v1/tempDir/191_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 637.77 .... ..... ... .... .....
# 1 . .. T 628.32 .... ..... ... .... .....
***************** Calibration iteration number 2 completed ************************
T 2513.77 .... ..... ... .... .....
# 1 . ..
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-resnet18-v1/tempDir/191_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 3863.65 .... ..... ... .... .....
# 1 . .. T 641.37 .... ..... ... .... .....
# 1 . .. T 637.52 .... ..... ... .... .....
***************** Calibration iteration number 3 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/cl-ort-resnet18-v1/tempDir/191_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 2467.16 .... ..... ... .... .....
***************** Calibration iteration number 3 completed ************************
T 635.57 .... ..... ... .... .....
# 1 . ..
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/od-ort-ssd-lite_mobilenetv2_fpn/tempDir/boxeslabels_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 637.23 .... ..... ... .... .....
***************** Calibration iteration number 4 completed ************************
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
substitute string tidl_net_ not found
****************************************************
** ALL MODEL CHECK PASSED **
****************************************************
Completed_Model : 1, Name : cl-ort-resnet18-v1 , Total time : 7018.86, Offload Time : 1188.73 , DDR RW MBs : 0, Output File : py_out_cl-ort-resnet18-v1_ADE_val_00001801.jpg
T 3806.35 .... ..... ... .... .....
***************** Calibration iteration number 2 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-ort-deeplabv3lite_mobilenetv2/tempDir/566TIDL_cast_out_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 2505.98 .... ..... ... .... .....
# 1 . .. T 2403.59 .... ..... ... .... .....
***************** Calibration iteration number 4 completed ************************
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
substitute string tidl_net_ not found
INFORMATION: [TIDL_ResizeLayer] Resize_153 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] Resize_156 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
****************************************************
** 2 WARNINGS 0 ERRORS **
****************************************************
Completed_Model : 4, Name : od-ort-ssd-lite_mobilenetv2_fpn , Total time : 17277.04, Offload Time : 2129.65 , DDR RW MBs : 0, Output File : py_out_od-ort-ssd-lite_mobilenetv2_fpn_ADE_val_00001801.jpg
T 3948.75 .... ..... ... .... .....
# 1 . .. T 3901.57 .... ..... ... .... .....
***************** Calibration iteration number 3 completed ************************
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/model-artifacts/ss-ort-deeplabv3lite_mobilenetv2/tempDir/566TIDL_cast_out_tidl_io_.qunat_stats_config.txt
----------------------- TIDL Process with REF_ONLY FLOW ------------------------
# 0 . .. T 3618.03 .... ..... ... .... .....
# 1 . .. T 3615.57 .... ..... ... .... .....
***************** Calibration iteration number 4 completed ************************
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
substitute string tidl_net_ not found
INFORMATION: [TIDL_ResizeLayer] 571 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
INFORMATION: [TIDL_ResizeLayer] 576 Any resize ratio which is power of 2 and greater than 4 will be placed by combination of 4x4 resize layer and 2x2 resize layer. For example a 8x8 resize will be replaced by 4x4 resize followed by 2x2 resize.
****************************************************
** 2 WARNINGS 0 ERRORS **
****************************************************
Completed_Model : 3, Name : ss-ort-deeplabv3lite_mobilenetv2 , Total time : 27679.58, Offload Time : 4512.37 , DDR RW MBs : 0, Output File : py_out_ss-ort-deeplabv3lite_mobilenetv2_ADE_val_00001801.jpg
Available execution providers : ['TIDLExecutionProvider', 'TIDLCompilationProvider', 'CPUExecutionProvider']
Running 4 Models - ['cl-ort-resnet18-v1', 'cl-ort-caffe_squeezenet_v1_1', 'ss-ort-deeplabv3lite_mobilenetv2', 'od-ort-ssd-lite_mobilenetv2_fpn']
Running_Model : cl-ort-resnet18-v1
Running_Model : cl-ort-caffe_squeezenet_v1_1
Running_Model : ss-ort-deeplabv3lite_mobilenetv2
Running_Model : od-ort-ssd-lite_mobilenetv2_fpn
libtidl_onnxrt_EP loaded 0x3a6ec80
libtidl_onnxrt_EP loaded 0x3502e30
2022-04-21 11:43:32.890967946 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891011938 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891018694 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891024159 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891029255 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891034446 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891040543 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891045626 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891050336 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891055306 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891060594 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891068208 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891073448 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891078092 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer1.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891082656 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891087428 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer4.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891092262 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891097790 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer3.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891102463 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2022-04-21 11:43:32.891107657 [W:onnxruntime:, graph.cc:3106 CleanUnusedInitializers] Removing initializer 'layer2.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
libtidl_onnxrt_EP loaded 0x35a3b00
libtidl_onnxrt_EP loaded 0x411adf0
Final number of subgraphs created are : 1, - Offloaded Nodes - 68, Total Nodes - 68
Final number of subgraphs created are : 1, - Offloaded Nodes - 124, Total Nodes - 124
0.0s: VX_ZONE_INIT:Enabled
0.16s: VX_ZONE_ERROR:Enabled
0.18s: VX_ZONE_WARNING:Enabled
0.426s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
0.0s: VX_ZONE_INIT:Enabled
0.9s: VX_ZONE_ERROR:Enabled
0.11s: VX_ZONE_WARNING:Enabled
0.348s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
Final number of subgraphs created are : 1, - Offloaded Nodes - 494, Total Nodes - 494
Final number of subgraphs created are : 1, - Offloaded Nodes - 52, Total Nodes - 52
0.0s: VX_ZONE_INIT:Enabled
0.10s: VX_ZONE_ERROR:Enabled
0.11s: VX_ZONE_WARNING:Enabled
0.392s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
0.0s: VX_ZONE_INIT:Enabled
0.9s: VX_ZONE_ERROR:Enabled
0.10s: VX_ZONE_WARNING:Enabled
0.325s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
, 0 0.518756 warplane, military plane ,, 1 0.321064 aircraft carrier, carrier, flattop, attack aircraft carrier ,, 2 0.108971 airliner ,, 3 0.020307 missile ,, 4 0.015969 projectile, missile ,
Saving image to ../../../output_images/
Completed_Model : 2, Name : cl-ort-caffe_squeezenet_v1_1 , Total time : 102.56, Offload Time : 102.51 , DDR RW MBs : 0, Output File : py_out_cl-ort-caffe_squeezenet_v1_1_airshow.jpg
, 0 23.311415 warplane, military plane ,, 1 22.239624 aircraft carrier, carrier, flattop, attack aircraft carrier ,, 2 18.488363 projectile, missile ,, 3 18.220415 missile ,, 4 15.540942 wing ,
Saving image to ../../../output_images/
Completed_Model : 1, Name : cl-ort-resnet18-v1 , Total time : 339.18, Offload Time : 339.15 , DDR RW MBs : 0, Output File : py_out_cl-ort-resnet18-v1_airshow.jpg
Saving image to ../../../output_images/
Completed_Model : 4, Name : od-ort-ssd-lite_mobilenetv2_fpn , Total time : 771.48, Offload Time : 771.40 , DDR RW MBs : 0, Output File : py_out_od-ort-ssd-lite_mobilenetv2_fpn_ADE_val_00001801.jpg
Saving image to ../../../output_images/
Completed_Model : 3, Name : ss-ort-deeplabv3lite_mobilenetv2 , Total time : 978.30, Offload Time : 978.25 , DDR RW MBs : 0, Output File : py_out_ss-ort-deeplabv3lite_mobilenetv2_ADE_val_00001801.jpg
Downloading ../../../models/public/mobilenetv2-1.0.onnx
Converted model is valid!
Traceback (most recent call last):
File "tvm_compilation_onnx_example.py", line 38, in <module>
from tvm import relay
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/__init__.py", line 26, in <module>
from ._ffi.base import TVMError, __version__
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/__init__.py", line 28, in <module>
from .base import register_error
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 71, in <module>
_LIB, _LIB_NAME = _load_lib()
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 57, in _load_lib
lib = ctypes.CDLL(lib_path[0], ctypes.RTLD_GLOBAL)
File "/usr/lib/python3.6/ctypes/__init__.py", line 348, in __init__
self._handle = _dlopen(self._name, mode)
OSError: libtinfo.so.5: cannot open shared object file: No such file or directory
Downloading ../../../models/public/inception_v3.tflite
/home/achavan8/Documents/Projects/AutoHitch/Model_Training/TI-DL-EVM_local/edgeai-tidl-tools/models/public/inception_v3.tflite
Traceback (most recent call last):
File "tvm_compilation_tflite_example.py", line 40, in <module>
from tvm import relay
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/__init__.py", line 26, in <module>
from ._ffi.base import TVMError, __version__
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/__init__.py", line 28, in <module>
from .base import register_error
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 71, in <module>
_LIB, _LIB_NAME = _load_lib()
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 57, in _load_lib
lib = ctypes.CDLL(lib_path[0], ctypes.RTLD_GLOBAL)
File "/usr/lib/python3.6/ctypes/__init__.py", line 348, in __init__
self._handle = _dlopen(self._name, mode)
OSError: libtinfo.so.5: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "tvm_compilation_onnx_example.py", line 38, in <module>
from tvm import relay
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/__init__.py", line 26, in <module>
from ._ffi.base import TVMError, __version__
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/__init__.py", line 28, in <module>
from .base import register_error
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 71, in <module>
_LIB, _LIB_NAME = _load_lib()
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 57, in _load_lib
lib = ctypes.CDLL(lib_path[0], ctypes.RTLD_GLOBAL)
File "/usr/lib/python3.6/ctypes/__init__.py", line 348, in __init__
self._handle = _dlopen(self._name, mode)
OSError: libtinfo.so.5: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "tvm_compilation_tflite_example.py", line 40, in <module>
from tvm import relay
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/__init__.py", line 26, in <module>
from ._ffi.base import TVMError, __version__
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/__init__.py", line 28, in <module>
from .base import register_error
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 71, in <module>
_LIB, _LIB_NAME = _load_lib()
File "/home/achavan8/.local/lib/python3.6/site-packages/tvm/_ffi/base.py", line 57, in _load_lib
lib = ctypes.CDLL(lib_path[0], ctypes.RTLD_GLOBAL)
File "/usr/lib/python3.6/ctypes/__init__.py", line 348, in __init__
self._handle = _dlopen(self._name, mode)
OSError: libtinfo.so.5: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "tvm_compilation_mxnet_example.py", line 37, in <module>
from gluoncv import model_zoo
ModuleNotFoundError: No module named 'gluoncv'
Running Inference on Model - ../../../model-artifacts/cl-dlr-tflite_inceptionnetv3
2022-04-21 12:44:46,130 ERROR error in DLRModel instantiation model_path ../../../model-artifacts/cl-dlr-tflite_inceptionnetv3 doesn't exist
Traceback (most recent call last):
File "/home/achavan8/.local/lib/python3.6/site-packages/dlr/api.py", line 89, in __init__
self._impl = DLRModelImpl(model_path, dev_type, dev_id, error_log_file, use_default_dlr)
File "/home/achavan8/.local/lib/python3.6/site-packages/dlr/dlr_model.py", line 65, in __init__
raise ValueError("model_path %s doesn't exist" % model_path)
ValueError: model_path ../../../model-artifacts/cl-dlr-tflite_inceptionnetv3 doesn't exist
Traceback (most recent call last):
File "dlr_inference_example.py", line 194, in <module>
postprocess_for_tflite_inceptionnetv3, 0)
File "dlr_inference_example.py", line 157, in model_create_and_run
model = DLRModel(model_dir, 'cpu')
File "/home/achavan8/.local/lib/python3.6/site-packages/dlr/api.py", line 92, in __init__
raise ex
File "/home/achavan8/.local/lib/python3.6/site-packages/dlr/api.py", line 89, in __init__
self._impl = DLRModelImpl(model_path, dev_type, dev_id, error_log_file, use_default_dlr)
File "/home/achavan8/.local/lib/python3.6/site-packages/dlr/dlr_model.py", line 65, in __init__
raise ValueError("model_path %s doesn't exist" % model_path)
ValueError: model_path ../../../model-artifacts/cl-dlr-tflite_inceptionnetv3 doesn't exist
X64 Architecture Running 1 Models - ['od-tfl-20220331_frozen_inference_graph_8b'] Running_Model : od-tfl-20220331_frozen_inference_graph_8b Warning : concat requires 4D input tensors - only 3 dims present.. Ignore if object detection network Number of subgraphs:48 , 163 nodes delegated out of 211 nodes ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** 0.0s: VX_ZONE_INIT:Enabled 0.4s: VX_ZONE_ERROR:Enabled 0.5s: VX_ZONE_WARNING:Enabled 0.305s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!! ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** 4.792553s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 4.792556s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 4.792558s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 4.792572s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 4.792574s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 4.792575s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 4.792576s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 4.792577s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 4.792757s: VX_ZONE_ERROR:[vxSetParameterByIndex:257] Invalid type 0x00000811! 4.792760s: VX_ZONE_ERROR:[vxSetParameterByIndex:306] Specified: parameter[1] type:00000811 => 0x7f35d23399d0 4.792761s: VX_ZONE_ERROR:[vxSetParameterByIndex:310] Required: parameter[1] dir:0 type:00000816 4.792782s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference 4.792837s: VX_ZONE_ERROR:[ownGraphNodeKernelValidate:531] node kernel validate failed for kernel com.ti.tidl at index 0 4.792839s: VX_ZONE_ERROR:[vxVerifyGraph:1941] Node kernel Validate failed 4.792841s: VX_ZONE_ERROR:[vxVerifyGraph:2109] Graph verify failed TIDL_RT_OVX: ERROR: Verifying TIDL graph ... Failed !!! TIDL_RT_OVX: ERROR: Verify OpenVX graph failed ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** 5.46680s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.46684s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.46688s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors 5.46690s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.46691s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.46693s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.46695s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.46697s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.46699s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.46701s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.46702s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.46712s: VX_ZONE_ERROR:[vxMapUserDataObject:473] Invalid user data object reference 5.46741s: VX_ZONE_ERROR:[vxUnmapUserDataObject:558] Invalid user data object reference 5.46746s: VX_ZONE_ERROR:[vxCreateNodeByStructure:96] failed to retrieve kernel enum 0 5.46749s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference 5.46750s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** 5.298480s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.298484s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.298487s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors 5.298488s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.298489s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.298490s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.298492s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.298493s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.298494s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.298514s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.298515s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.298524s: VX_ZONE_ERROR:[vxMapUserDataObject:473] Invalid user data object reference 5.298526s: VX_ZONE_ERROR:[vxUnmapUserDataObject:558] Invalid user data object reference 5.298530s: VX_ZONE_ERROR:[vxCreateNodeByStructure:96] failed to retrieve kernel enum 0 5.298531s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference 5.298533s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference ************** Frame index 1 : Running float import ************* WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target. **************************************************** ** 1 WARNINGS 0 ERRORS ** **************************************************** 5.552226s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.552230s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.552233s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors 5.552254s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.552256s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.552259s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.552261s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.552262s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.552264s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.552265s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h 5.552266s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object 5.552281s: VX_ZONE_ERROR:[ownTensorCheckSizes:189] Invalid view parameter(s) in dimension: 1
Hi Akash, "run_python_examples.sh" does compilation an inference for ONNX RT, TFLite, and DLR. I think your model is TFLite.
So, I propose to run only that demo. For that you can comment out ONNX and DLR from "run_python_examples.sh" or you can run directly "tflrt_delegate.py"
https://github.com/TexasInstruments/edgeai-tidl-tools/blob/c6987ebeb67e48323a1e9e62f855d35c9da9d5d5/scripts/run_python_examples.sh#L14
cd $CURDIR/examples/osrt_python/tfl
python3 tflrt_delegate.py -c
python3 tflrt_delegate.py
By the way, I only see the 3 OOB models listed in TFLite from your log, I don't see yours..
Running 3 Models - ['cl-tfl-mobilenet_v1_1.0_224', 'ss-tfl-deeplabv3_mnv2_ade20k_float', 'od-tfl-ssd_mobilenet_v2_300_float']
You could also only run your model by modifying models list:
https://github.com/TexasInstruments/edgeai-tidl-tools/blob/c6987ebeb67e48323a1e9e62f855d35c9da9d5d5/examples/osrt_python/tfl/tflrt_delegate.py#L213
thank you,
Paula
Hello Paula,
I had uploaded to two logs. The second log is from the compilation step of my custom model. The compilation never finished, it stuck.
Below is the log when I ran python3.6 tflrt_delegate.py -c
python3.6 tflrt_delegate.py -c
Running 1 Models - ['od-tfl-20220331_frozen_inference_graph_8b']
Running_Model : od-tfl-20220331_frozen_inference_graph_8b
Warning : concat requires 4D input tensors - only 3 dims present.. Ignore if object detection network
Number of subgraphs:48 , 163 nodes delegated out of 211 nodes
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.5s: VX_ZONE_ERROR:Enabled
0.6s: VX_ZONE_WARNING:Enabled
0.287s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
4.653591s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.653595s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.653597s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.653599s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.653600s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.653601s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.653603s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.653604s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.653743s: VX_ZONE_ERROR:[vxSetParameterByIndex:257] Invalid type 0x00000811!
4.653746s: VX_ZONE_ERROR:[vxSetParameterByIndex:306] Specified: parameter[1] type:00000811 => 0x7f752d6969d0
4.653748s: VX_ZONE_ERROR:[vxSetParameterByIndex:310] Required: parameter[1] dir:0 type:00000816
4.653750s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
4.653784s: VX_ZONE_ERROR:[ownGraphNodeKernelValidate:531] node kernel validate failed for kernel com.ti.tidl at index 0
4.653786s: VX_ZONE_ERROR:[vxVerifyGraph:1941] Node kernel Validate failed
4.653787s: VX_ZONE_ERROR:[vxVerifyGraph:2109] Graph verify failed
TIDL_RT_OVX: ERROR: Verifying TIDL graph ... Failed !!!
TIDL_RT_OVX: ERROR: Verify OpenVX graph failed
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
4.904795s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.904800s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.904803s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors
4.904804s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.904805s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.904807s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.904808s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.904809s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.904810s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.904811s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.904813s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.904822s: VX_ZONE_ERROR:[vxMapUserDataObject:473] Invalid user data object reference
4.904825s: VX_ZONE_ERROR:[vxUnmapUserDataObject:558] Invalid user data object reference
4.904829s: VX_ZONE_ERROR:[vxCreateNodeByStructure:96] failed to retrieve kernel enum 0
4.904831s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
4.904832s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
5.146370s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.146376s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.146379s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors
5.146381s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.146382s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.146383s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.146384s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.146385s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.146387s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.146388s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.146389s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.146398s: VX_ZONE_ERROR:[vxMapUserDataObject:473] Invalid user data object reference
5.146400s: VX_ZONE_ERROR:[vxUnmapUserDataObject:558] Invalid user data object reference
5.146404s: VX_ZONE_ERROR:[vxCreateNodeByStructure:96] failed to retrieve kernel enum 0
5.146405s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
5.146406s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
5.390302s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.390306s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.390309s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors
5.390311s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.390312s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.390313s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.390314s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.390315s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.390317s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.390318s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.390319s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.390332s: VX_ZONE_ERROR:[ownTensorCheckSizes:189] Invalid view parameter(s) in dimension: 1
Hi Akash, my bad, I missed the second log before. We will take a look.
Thank you,
Paula
Hi Akash, perfect timing =). I was about to update you. We got a potential fix. I will share with you a new tidl_model_import_tflite.so w/ this patch. I will target send it soon (next few hours).
thank you,
Paula
Akash, can you send me your email address? in order to invite you to a ti.box share folder
thank you,
Paula
Akash, you will get an email to accept ti.box. Let me know if you face any issues downloading the lib.
After downloading patched TIDL model import libs please replace them inside edgeai-tidl-tools "tidl_tools" folder and re-test your model. Please let us know if compilation is successful and if you can run inference.
thank you,
Paula
Paula,
I am seeing the same behavior with new libs. The model doesn't compile. Below is the log
python3.6 tflrt_delegate.py -c
Running 1 Models - ['od-tfl-20220331_frozen_inference_graph_8b']
Running_Model : od-tfl-20220331_frozen_inference_graph_8b
Warning : concat requires 4D input tensors - only 3 dims present.. Ignore if object detection network
Number of subgraphs:48 , 163 nodes delegated out of 211 nodes
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
0.0s: VX_ZONE_INIT:Enabled
0.17s: VX_ZONE_ERROR:Enabled
0.17s: VX_ZONE_WARNING:Enabled
0.490s: VX_ZONE_INIT:[tivxInit:178] Initialization Done !!!
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
4.802218s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.802222s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.802224s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.802225s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.802226s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.802227s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.802229s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
4.802230s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
4.802403s: VX_ZONE_ERROR:[vxSetParameterByIndex:257] Invalid type 0x00000811!
4.802406s: VX_ZONE_ERROR:[vxSetParameterByIndex:306] Specified: parameter[1] type:00000811 => 0x7f2c6f8cf9d0
4.802408s: VX_ZONE_ERROR:[vxSetParameterByIndex:310] Required: parameter[1] dir:0 type:00000816
4.802431s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
4.802467s: VX_ZONE_ERROR:[ownGraphNodeKernelValidate:531] node kernel validate failed for kernel com.ti.tidl at index 0
4.802469s: VX_ZONE_ERROR:[vxVerifyGraph:1941] Node kernel Validate failed
4.802471s: VX_ZONE_ERROR:[vxVerifyGraph:2109] Graph verify failed
TIDL_RT_OVX: ERROR: Verifying TIDL graph ... Failed !!!
TIDL_RT_OVX: ERROR: Verify OpenVX graph failed
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
5.54595s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.54600s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.54622s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors
5.54624s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.54626s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.54628s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.54650s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.54653s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.54654s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.54656s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.54657s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.54666s: VX_ZONE_ERROR:[vxMapUserDataObject:473] Invalid user data object reference
5.54669s: VX_ZONE_ERROR:[vxUnmapUserDataObject:558] Invalid user data object reference
5.54673s: VX_ZONE_ERROR:[vxCreateNodeByStructure:96] failed to retrieve kernel enum 0
5.54676s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
5.54677s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
5.306544s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.306548s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.306551s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors
5.306553s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.306554s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.306570s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.306571s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.306573s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.306574s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.306575s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.306576s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.306604s: VX_ZONE_ERROR:[vxMapUserDataObject:473] Invalid user data object reference
5.306626s: VX_ZONE_ERROR:[vxUnmapUserDataObject:558] Invalid user data object reference
5.306631s: VX_ZONE_ERROR:[vxCreateNodeByStructure:96] failed to retrieve kernel enum 0
5.306633s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
5.306634s: VX_ZONE_ERROR:[vxSetReferenceName:659] Invalid reference
************** Frame index 1 : Running float import *************
WARNING: [TIDL_E_DATAFLOW_INFO_NULL] ti_cnnperfsim.out fails to allocate memory in MSMC. Please look into perfsim log. This model can only be used on PC emulation, it will get fault on target.
****************************************************
** 1 WARNINGS 0 ERRORS **
****************************************************
5.558158s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.558162s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.558185s: VX_ZONE_ERROR:[tivxAddKernelTIDL:259] invalid values for num_input_tensors or num_output_tensors
5.558187s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.558189s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.558191s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.558192s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.558194s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.558196s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.558198s: VX_ZONE_WARNING:[ownAllocObject:765] May need to increase the value of TIVX_USER_DATA_OBJECT_MAX_OBJECTS in tiovx/include/TI/tivx_config.h
5.558200s: VX_ZONE_ERROR:[ownCreateReference:342] Failed to allocate reference object
5.558214s: VX_ZONE_ERROR:[ownTensorCheckSizes:189] Invalid view parameter(s) in dimension: 1
Hi Akash, it is still creating 48 subgraphs.. It is any way you can share this model with us? or a way to reproduce it (maybe a cut version of your model)?
thank you,
Paula
Hi Akash, let me give you some updates. From shared model we see there are some "FakeQuantWithMinMaxVars" nodes which are not supported. This seems to be the cause of 48 subgraphs being created even after shared Relu fix.
We support maximum 16 subgraphs in TIDL, however, the rest of the subgraphs should have run in ARM. We need to check why it is not the case.
In any case, running 16 subgraphs and the rest on ARM probably will have a huge performance penalty. Therefore, do you think "FakeQuantWithMinMaxVars" could be replaced for some other supported operator(s) in TIDL?
thank you,
Paula
Hello Paula,
Thanks for the update. I will check internally how to proceed and let you know.
Thank you,
Akash