TDA4VM: Questions about ModelMaker

You have to use the appropriate branch in modelmaker repository, for example: github.com/.../r8.6

I'm trying to work with 9.0 for now.

github.com/.../r9.0

It installed as per the procedure.

./run_modelmaker.sh TDA4VM config_classification.yaml

When I train the model with the built-in config_classification, train says it's done, but I get an error during the package process.

I'll post the log below.

(py310) rex@pkb36:~/edgeai-modelmaker$ ./run_modelmaker.sh TDA4VM config_classification.yaml
Number of AVX cores detected in PC: 24
AVX compilation speedup in PC : 1
Target device : TDA4VM
PYTHONPATH : .:
TIDL_TOOLS_PATH : ../edgeai-benchmark/tools/TDA4VM/tidl_tools
LD_LIBRARY_PATH : ../edgeai-benchmark/tools/TDA4VM/tidl_tools
argv: ['./scripts/run_modelmaker.py', 'config_classification.yaml', '--target_device', 'TDA4VM']
---------------------------------------------------------------------
Run Name: 20240408-151318/mobilenet_v2_lite
- Model: mobilenet_v2_lite
- TargetDevices & Estimated Inference Times (ms): {'TDA4VM': 2.27, 'AM62A': 4.03, 'AM68A': 2.16, 'AM69A': '2.02 (with 1/4th device capability)', 'AM62': 172.92}
- This model can be compiled for the above device(s).
---------------------------------------------------------------------
downloading from software-dl.ti.com/.../mobilenet_v2_20191224_checkpoint.pth to ./data/downloads/pretrained/mobilenet_v2_lite/mobilenet_v2_20191224_checkpoint.pth
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 28263629/28263629 [00:01<00:00, 15877892.69B/s]
downloading from software-dl.ti.com/.../animal_classification.zip to ./data/downloads/datasets/animal_classification.zip
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27716536/27716536 [00:00<00:00, 51885378.75B/s]
dataset split sizes {'train': 84, 'val': 21}
max_num_files is set to: 10000
dataset split sizes are limited to: {'train': 84, 'val': 21}
dataset loading OK
Run params is at: /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/run.yaml
Not using distributed mode
Namespace(data_path='/home/rex/edgeai-modelmaker/data/projects/animal_classification/dataset', dataset='modelmaker', annotation_prefix='instances', model='mobilenet_v2_lite', device='cpu', gpus=0, batch_size=64, epochs=15, workers=16, opt='sgd', lr=0.002, momentum=0.9, weight_decay=0.0001, norm_weight_decay=None, bias_weight_decay=None, transformer_embedding_decay=None, label_smoothing=0.0, mixup_alpha=0.0, cutmix_alpha=0.0, lr_scheduler='steplr', lr_warmup_epochs=1, lr_warmup_method='constant', lr_warmup_decay=0.01, lr_step_size=30, lr_gamma=0.1, lr_min=0.0, print_freq=100, output_dir='/home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training', resume='', start_epoch=0, cache_dataset=False, sync_bn=False, test_only=False, auto_augment=None, ra_magnitude=9, augmix_severity=3, random_erase=0.0, amp=False, world_size=1, dist_url='env://', distributed=False, parallel=0, model_ema=False, model_ema_steps=32, model_ema_decay=0.99998, use_deterministic_algorithms=False, interpolation='bilinear', val_resize_size=256, val_crop_size=224, train_crop_size=224, clip_grad_norm=None, ra_sampler=False, ra_reps=3, weights='./data/downloads/pretrained/mobilenet_v2_lite/mobilenet_v2_20191224_checkpoint.pth', model_surgery=1, quantization=0, quantization_type=None, pruning=0, pruning_ratio=0.5, pruning_type=1, compile_model=0, opset_version=11, train_epoch_size_factor=0.0, val_epoch_size_factor=0.0, quit_event=None, weights_url='./data/downloads/pretrained/mobilenet_v2_lite/mobilenet_v2_20191224_checkpoint.pth', weights_enum=None)
Loading data
Loading training data
Took 0.0005164146423339844
Loading validation data
Creating data loaders
Creating model
loading pretrained checkpoint from: ./data/downloads/pretrained/mobilenet_v2_lite/mobilenet_v2_20191224_checkpoint.pth
=> The shape of the following weights did not match:
classifier.1.weight
classifier.1.bias
=> WARNING: weights could not be loaded completely.
Start training
Epoch: [0] [0/2] eta: 0:00:18 lr: 2e-05 img/s: 7.850357097276941 loss: 0.7521 (0.7521) acc1: 37.5000 (37.5000) acc5: 100.0000 (100.0000) time: 9.1248 data: 0.9722
Epoch: [0] Total time: 0:00:11
/home/rex/.pyenv/versions/py310/lib/python3.10/site-packages/torch/optim/lr_scheduler.py:152: UserWarning: The epoch parameter in `scheduler.step()` was not necessary and is being deprecated where possible. Please use `scheduler.step()` to step the scheduler. During the deprecation, if epoch is different from None, the closed form is used instead of the new chainable form, where available. Please open an issue if you are unable to replicate your use case: github.com/.../choose.
warnings.warn(EPOCH_DEPRECATION_WARNING, UserWarning)
Test: [0/1] eta: 0:00:01 loss: 0.6541 (0.6541) acc1: 52.3810 (52.3810) acc5: 100.0000 (100.0000) time: 1.5696 data: 0.7389
Test: Total time: 0:00:01
Test: Acc@1 52.381 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [1] [0/2] eta: 0:00:18 lr: 0.002 img/s: 7.901261173774527 loss: 0.7398 (0.7398) acc1: 45.3125 (45.3125) acc5: 100.0000 (100.0000) time: 9.1888 data: 1.0888
Epoch: [1] Total time: 0:00:11
Test: [0/1] eta: 0:00:01 loss: 0.5937 (0.5937) acc1: 57.1429 (57.1429) acc5: 100.0000 (100.0000) time: 1.2760 data: 0.6156
Test: Total time: 0:00:01
Test: Acc@1 57.143 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [2] [0/2] eta: 0:00:18 lr: 0.002 img/s: 7.85802989263438 loss: 0.6453 (0.6453) acc1: 64.0625 (64.0625) acc5: 100.0000 (100.0000) time: 9.4716 data: 1.3270
Epoch: [2] Total time: 0:00:11
Test: [0/1] eta: 0:00:01 loss: 0.5176 (0.5176) acc1: 71.4286 (71.4286) acc5: 100.0000 (100.0000) time: 1.3306 data: 0.6436
Test: Total time: 0:00:01
Test: Acc@1 71.429 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [3] [0/2] eta: 0:00:20 lr: 0.002 img/s: 7.06897170027632 loss: 0.5534 (0.5534) acc1: 67.1875 (67.1875) acc5: 100.0000 (100.0000) time: 10.1106 data: 1.0569
Epoch: [3] Total time: 0:00:12
Test: [0/1] eta: 0:00:02 loss: 0.3470 (0.3470) acc1: 90.4762 (90.4762) acc5: 100.0000 (100.0000) time: 2.0029 data: 1.1219
Test: Total time: 0:00:02
Test: Acc@1 90.476 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [4] [0/2] eta: 0:00:21 lr: 0.002 img/s: 6.8151538236518885 loss: 0.4411 (0.4411) acc1: 89.0625 (89.0625) acc5: 100.0000 (100.0000) time: 10.9387 data: 1.5479
Epoch: [4] Total time: 0:00:13
Test: [0/1] eta: 0:00:01 loss: 0.2966 (0.2966) acc1: 95.2381 (95.2381) acc5: 100.0000 (100.0000) time: 1.4435 data: 0.6641
Test: Total time: 0:00:01
Test: Acc@1 95.238 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [5] [0/2] eta: 0:00:20 lr: 0.002 img/s: 7.055271486679993 loss: 0.4692 (0.4692) acc1: 75.0000 (75.0000) acc5: 100.0000 (100.0000) time: 10.4801 data: 1.4087
Epoch: [5] Total time: 0:00:12
Test: [0/1] eta: 0:00:01 loss: 0.2324 (0.2324) acc1: 90.4762 (90.4762) acc5: 100.0000 (100.0000) time: 1.4338 data: 0.7108
Test: Total time: 0:00:01
Test: Acc@1 90.476 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [6] [0/2] eta: 0:00:19 lr: 0.002 img/s: 7.722963373418965 loss: 0.3505 (0.3505) acc1: 89.0625 (89.0625) acc5: 100.0000 (100.0000) time: 9.7330 data: 1.4460
Epoch: [6] Total time: 0:00:12
Test: [0/1] eta: 0:00:01 loss: 0.2410 (0.2410) acc1: 90.4762 (90.4762) acc5: 100.0000 (100.0000) time: 1.3284 data: 0.6507
Test: Total time: 0:00:01
Test: Acc@1 90.476 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [7] [0/2] eta: 0:00:18 lr: 0.002 img/s: 7.989992041125999 loss: 0.2540 (0.2540) acc1: 90.6250 (90.6250) acc5: 100.0000 (100.0000) time: 9.1905 data: 1.1804
Epoch: [7] Total time: 0:00:11
Test: [0/1] eta: 0:00:01 loss: 0.3127 (0.3127) acc1: 90.4762 (90.4762) acc5: 100.0000 (100.0000) time: 1.4043 data: 0.7409
Test: Total time: 0:00:01
Test: Acc@1 90.476 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [8] [0/2] eta: 0:00:18 lr: 0.002 img/s: 7.920137556152451 loss: 0.3176 (0.3176) acc1: 81.2500 (81.2500) acc5: 100.0000 (100.0000) time: 9.3999 data: 1.3192
Epoch: [8] Total time: 0:00:11
Test: [0/1] eta: 0:00:01 loss: 0.2673 (0.2673) acc1: 90.4762 (90.4762) acc5: 100.0000 (100.0000) time: 1.4153 data: 0.6784
Test: Total time: 0:00:01
Test: Acc@1 90.476 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [9] [0/2] eta: 0:00:18 lr: 0.002 img/s: 7.947269783586295 loss: 0.2317 (0.2317) acc1: 90.6250 (90.6250) acc5: 100.0000 (100.0000) time: 9.4466 data: 1.3935
Epoch: [9] Total time: 0:00:11
Test: [0/1] eta: 0:00:01 loss: 0.1854 (0.1854) acc1: 95.2381 (95.2381) acc5: 100.0000 (100.0000) time: 1.5771 data: 0.7197
Test: Total time: 0:00:01
Test: Acc@1 95.238 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [10] [0/2] eta: 0:00:20 lr: 0.002 img/s: 7.280894329417983 loss: 0.1709 (0.1709) acc1: 95.3125 (95.3125) acc5: 100.0000 (100.0000) time: 10.1891 data: 1.3989
Epoch: [10] Total time: 0:00:12
Test: [0/1] eta: 0:00:01 loss: 0.1476 (0.1476) acc1: 95.2381 (95.2381) acc5: 100.0000 (100.0000) time: 1.2314 data: 0.6176
Test: Total time: 0:00:01
Test: Acc@1 95.238 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [11] [0/2] eta: 0:00:17 lr: 0.002 img/s: 8.600956201314613 loss: 0.1941 (0.1941) acc1: 93.7500 (93.7500) acc5: 100.0000 (100.0000) time: 8.8015 data: 1.3604
Epoch: [11] Total time: 0:00:10
Test: [0/1] eta: 0:00:01 loss: 0.1480 (0.1480) acc1: 90.4762 (90.4762) acc5: 100.0000 (100.0000) time: 1.3716 data: 0.7031
Test: Total time: 0:00:01
Test: Acc@1 90.476 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [12] [0/2] eta: 0:00:17 lr: 0.002 img/s: 8.332354969669298 loss: 0.2010 (0.2010) acc1: 95.3125 (95.3125) acc5: 100.0000 (100.0000) time: 8.8156 data: 1.1347
Epoch: [12] Total time: 0:00:10
Test: [0/1] eta: 0:00:01 loss: 0.1601 (0.1601) acc1: 95.2381 (95.2381) acc5: 100.0000 (100.0000) time: 1.2367 data: 0.5897
Test: Total time: 0:00:01
Test: Acc@1 95.238 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [13] [0/2] eta: 0:00:18 lr: 0.002 img/s: 8.465442472238657 loss: 0.1686 (0.1686) acc1: 93.7500 (93.7500) acc5: 100.0000 (100.0000) time: 9.0140 data: 1.4538
Epoch: [13] Total time: 0:00:10
Test: [0/1] eta: 0:00:01 loss: 0.1801 (0.1801) acc1: 95.2381 (95.2381) acc5: 100.0000 (100.0000) time: 1.3876 data: 0.6112
Test: Total time: 0:00:01
Test: Acc@1 95.238 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Epoch: [14] [0/2] eta: 0:00:17 lr: 0.002 img/s: 8.316234926026885 loss: 0.1318 (0.1318) acc1: 96.8750 (96.8750) acc5: 100.0000 (100.0000) time: 8.7830 data: 1.0872
Epoch: [14] Total time: 0:00:10
Test: [0/1] eta: 0:00:01 loss: 0.1934 (0.1934) acc1: 95.2381 (95.2381) acc5: 100.0000 (100.0000) time: 1.3030 data: 0.6799
Test: Total time: 0:00:01
Test: Acc@1 95.238 Acc@5 100.000
============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ==============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Training time 0:03:26
Trained model is at: /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training

SUCCESS: ModelMaker - Training completed.

INFO:20240408-151652: model import is in progress - please see the log file for status.
configs to run: ['cl-6090']
number of configs: 1

INFO:20240408-151652: parallel_run - parallel_processes:1 parallel_devices=[0]
TASKS | | 0% 0/1| [< ]
INFO:20240408-151652: starting process on parallel_device - 0 0%| || 0/1 [00:00<?, ?it/s]

INFO:20240408-151652: starting - cl-6090
INFO:20240408-151652: model_path - /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training/model.onnx
INFO:20240408-151652: model_file - /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/compilation/TDA4VM/work/cl-6090/model/model.onnx
INFO:20240408-151652: quant_file - /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/compilation/TDA4VM/work/cl-6090/model/model_qparams.prototxt
Downloading 1/1: /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training/model.onnx
Download done for /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training/model.onnx
Downloading 1/1: /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training/model.onnx
Download done for /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training/model.onnx
Converted model is valid!

INFO:20240408-151652: running - cl-6090
INFO:20240408-151652: pipeline_config - {'task_type': 'classification', 'dataset_category': 'imagenet', 'calibration_dataset': <edgeai_benchmark.datasets.modelmaker_datasets.ModelMakerClassificationDataset object at 0x7f6f26e90130>, 'input_dataset': <edgeai_benchmark.datasets.modelmaker_datasets.ModelMakerClassificationDataset object at 0x7f6f26e92050>, 'postprocess': <edgeai_benchmark.postprocess.PostProcessTransforms object at 0x7f6f26e93a00>, 'preprocess': <edgeai_benchmark.preprocess.PreProcessTransforms object at 0x7f6f264ccf40>, 'session': <edgeai_benchmark.sessions.onnxrt_session.ONNXRTSession object at 0x7f6f264cd210>, 'model_info': {'metric_reference': {'accuracy_top1%': None}, 'model_shortlist': 20}, 'metric': {'label_offset_pred': 1}}
TASKS | 100%|██████████|| 1/1 [00:00<00:00, 1.95it/s]

INFO:20240408-151653: model inference is in progress - please see the log file for status.
configs to run: ['cl-6090']
number of configs: 1

INFO:20240408-151653: parallel_run - parallel_processes:1 parallel_devices=[0]
TASKS | | 0% 0/1| [< ]
INFO:20240408-151653: starting process on parallel_device - 0 0%| || 0/1 [00:00<?, ?it/s]

INFO:20240408-151653: starting - cl-6090
INFO:20240408-151653: model_path - /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/training/model.onnx
INFO:20240408-151653: model_file - /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/compilation/TDA4VM/work/cl-6090/model/model.onnx
INFO:20240408-151653: quant_file - /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/compilation/TDA4VM/work/cl-6090/model/model_qparams.prototxt

INFO:20240408-151653: running - cl-6090
INFO:20240408-151653: pipeline_config - {'task_type': 'classification', 'dataset_category': 'imagenet', 'calibration_dataset': <edgeai_benchmark.datasets.modelmaker_datasets.ModelMakerClassificationDataset object at 0x7f6f26e90130>, 'input_dataset': <edgeai_benchmark.datasets.modelmaker_datasets.ModelMakerClassificationDataset object at 0x7f6f26e92050>, 'postprocess': <edgeai_benchmark.postprocess.PostProcessTransforms object at 0x7f6f26e93a00>, 'preprocess': <edgeai_benchmark.preprocess.PreProcessTransforms object at 0x7f6f264ccf40>, 'session': <edgeai_benchmark.sessions.onnxrt_session.ONNXRTSession object at 0x7f6f264cd210>, 'model_info': {'metric_reference': {'accuracy_top1%': None}, 'model_shortlist': 20}, 'metric': {'label_offset_pred': 1}}
TASKS | 100%|██████████|| 1/1 [00:00<00:00, 2.41it/s]

packaging artifacts to /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/compilation/TDA4VM/pkg please wait...
WARNING:20240408-151653: could not package - /home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/compilation/TDA4VM/work/cl-6090
Traceback (most recent call last):
File "/home/rex/edgeai-modelmaker/./scripts/run_modelmaker.py", line 137, in <module>
main(config)
File "/home/rex/edgeai-modelmaker/./scripts/run_modelmaker.py", line 76, in main
model_runner.run()
File "/home/rex/edgeai-modelmaker/edgeai_modelmaker/ai_modules/vision/runner.py", line 187, in run
self.model_compilation.run()
File "/home/rex/edgeai-modelmaker/edgeai_modelmaker/ai_modules/vision/compilation/edgeai_benchmark.py", line 262, in run
edgeai_benchmark.interfaces.package_artifacts(self.settings, self.work_dir, out_dir=self.package_dir, custom_model=True)
File "/home/rex/edgeai-benchmark/edgeai_benchmark/interfaces/run_package.py", line 271, in package_artifacts
with open(os.path.join(out_dir,'artifacts.yaml'), 'w') as fp:
FileNotFoundError: [Errno 2] No such file or directory: '/home/rex/edgeai-modelmaker/data/projects/animal_classification/run/20240408-151318/mobilenet_v2_lite/compilation/TDA4VM/pkg/artifacts.yaml'

Do you still see the issue or could resolve on your own?