search

Daniil-Osokin / lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
Apache License 2.0
656 stars 138 forks source link

Converting to OpenVINO format #14

Closed kyang-06 closed 4 years ago

kyang-06 commented 4 years ago

Hi, thank you for the elegant implementation into OpenVINO framework! I encountered converting issue in inference with OpenVINO step 3 as: [ ERROR ] Cannot pre-process ONNX graph after reading from model file "ProjectPath\human-pose-estimation-3d.onnx". File is corrupt or has unsupported format. Details: 'Graph' object has no attribute 'node' In step 2, the ONNX converting script print long log list with module layer shape, and some weird messge like: %401 : Float(1, 32, 128, 224) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[2, 2]](%data, %model.0.0.weight) # C:\Users\envyi\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\nn\modules\conv.py:342:0

My OS is Windows 10, and the demo runs normally. Looking forward to your help.

Daniil-Osokin commented 4 years ago

Hi, try to install networkx 2.3: pip3 install networkx==2.3. Looks like it is a special OpenVINO dependency.

Daniil-Osokin commented 4 years ago

Hope, it helped.