Hi Team,
For your reference i am attaching the model and config file please help me with following error.
INFO : No Mata Arch Layer to parse
ONNX Model (Proto) File : ../../test/testvecs/models/public/onnx/model.onnx
TIDL Network File : ../../test/testvecs/config/tidl_models/onnx/tidl_net_pele.bin
TIDL IO Info File : ../../test/testvecs/config/tidl_models/onnx/tidl_io_pele_
Current ONNX OpSet Version : 9
Could not find const or initializer 1233 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1149 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1157 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1165 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1173 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1181 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1190 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1198 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1206 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1214 !!!
Only float and INT64 tensor is suported
Could not find const or initializer 1222 !!!
Only float and INT64 tensor is suported
Warning : Merging Pad layer with Average Pooling layer. This is expected to work but this flow is functionally not validated with ONNX model format.
Warning : Merging Pad layer with Average Pooling layer. This is expected to work but this flow is functionally not validated with ONNX model format.
Warning : Merging Pad layer with Average Pooling layer. This is expected to work but this flow is functionally not validated with ONNX model format.
In put of TIDL_SoftMaxLayer layer needs to be Faltten. Please add Flatten layer to import this mdoels. Except SSD.
Could not find Meta Arch confg file
~~~~~Running TIDL in PC emulation mode to collect Activations range for each layer~~~~~
Processing config file #0 : /home/user/ti-processor-sdk-rtos-j721e-evm-07_01_00_11/tidl_j7_01_03_00_11/ti_dl/test/testvecs/config/tidl_models/onnx/tidl_import_pelenet.txt.qunat_stats_config.txt
Error at line: 694 : in file /opt/Jenkins_OUT/workspace/J7_TIDL_Child_3/c7x-mma-tidl/ti_dl/release/tidl_j7_01_03_00_11/ti_dl/test/src/pc_linux/../tidl_rt.c, of function : TIDLRT_create
Error Type: TIDL_E_UNSUPPORTED_LAYER
Error at line: 437 : in file /opt/Jenkins_OUT/workspace/J7_TIDL_Child_3/c7x-mma-tidl/ti_dl/release/tidl_j7_01_03_00_11/ti_dl/test/src/pc_linux/../tidl_tb.c, of function : tidlMultiInstanceTest
Error Type: TIDL_E_UNSUPPORTED_LAYER
------------------ Network Compiler Traces -----------------------------
successful Memory allocation
-------------------- Network Compiler : Analysis Results are available --------------------
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_TransposeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_ReshapeLayer] should be removed in import process. If not, this model will not work!
ERROR: [TIDL_SoftMaxLayer] input shape of softmax must be 1x1x1xN.
ERROR: TIDL_E_QUANT_STATS_NOT_AVAILABLE] tidl_quant_stats_tool.out fails to collect dynamic range. Please look into quant stats log. This model will get fault on target.
****************************************************
** 0 WARNINGS 24 ERRORS **
****************************************************
modelType = 2 numParamBits = 8 numFeatureBits = 8 quantizationStyle = 3 #quantizationStyle = 2 inWidth = 304 inHeight = 304 inNumChannels = 3 inputNetFile = "../../test/testvecs/models/public/onnx/model.onnx" outputNetFile = "../../test/testvecs/config/tidl_models/onnx/tidl_net_pele.bin" outputParamsFile = "../../test/testvecs/config/tidl_models/onnx/tidl_io_pele_" inDataNorm = 1 inMean = 104 117 123 inScale = 0.0170000009239 0.0170000009239 0.0170000009239 numFrames = 1 inData = "../../test/testvecs/config/detection_list.txt" perfSimConfig = ../../test/testvecs/config/import/device_config.cfg inElementType = 0 #outDataNamesList = "convolution_output,convolution_output1,convolution_output2" metaArchType = 1 #metaLayersNamesList = "../../test/testvecs/config/import/public/onnx/tidl_import_yolo3_metaarch.prototxt" postProcType = 2 #metaLayersNamesList = ../../test/testvecs/models/public/onnx/rfb_mobilenet_v2_coco.prototxt
