Facing problem while converting Darknet weights to ONNX model for YOLOv3

[shreyapamecha]

!python3 detect.py --cfg cfg/yolov3_counter_detection.cfg --weights weights/yolov3_counter_detection.weights

I ran this code on Google Colab.

The error which I got is:

Namespace(cfg='cfg/yolov3_counter_detection.cfg', conf_thres=0.3, data='data/coco.data', device='', fourcc='mp4v', half=False, nms_thres=0.5, output='output', source='data/samples', view_img=False, weights='weights/yolov3_counter_detection.weights') Using CPU

Traceback (most recent call last): File "detect.py", line 174, in detect() File "detect.py", line 48, in detect torch.onnx.export(model, img, 'weights/export.onnx', verbose=True, opset_version=9) File "/usr/local/lib/python3.6/dist-packages/torch/onnx/init.py", line 230, in export custom_opsets, enable_onnx_checker, use_external_data_format) File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 91, in export use_external_data_format=use_external_data_format) File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 639, in _export dynamic_axes=dynamic_axes) File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 411, in _model_to_graph use_new_jit_passes) File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 379, in _create_jit_graph graph, torch_out = _trace_and_get_graph_from_model(model, args) File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 342, in _trace_and_get_graph_from_model torch.jit._get_trace_graph(model, args, strict=False, _force_outplace=False, _return_inputs_states=True) File "/usr/local/lib/python3.6/dist-packages/torch/jit/_trace.py", line 1148, in _get_trace_graph outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/jit/_trace.py", line 130, in forward self._force_outplace, File "/usr/local/lib/python3.6/dist-packages/torch/jit/_trace.py", line 116, in wrapper outs.append(self.inner(trace_inputs)) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 725, in _call_impl result = self._slow_forward(input, kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 709, in _slow_forward result = self.forward(*input, kwargs) File "/content/gdrive/My Drive/Internship_SecureMeters/TFlite/onnx_tflite_yolov3/models.py", line 249, in forward x = module(x, img_size) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 725, in _call_impl result = self._slow_forward(*input, *kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 709, in _slow_forward result = self.forward(input, **kwargs) File "/content/gdrive/My Drive/Internship_SecureMeters/TFlite/onnx_tflite_yolov3/models.py", line 203, in forward p_cls = torch.cat(p_cls0, io[..., 6:], -1) TypeError: cat() received an invalid combination of arguments - got (int, Tensor, int), but expected one of:

• (tuple of Tensors tensors, name dim, *, Tensor out)
• (tuple of Tensors tensors, int dim, *, Tensor out)

[zldrobit]

Could you share your notebook， so I can debug through your operations？

[shreyapamecha]

Thank you for your reply. It is difficult for me to share the notebook. I can tell you the steps I followed:

Installation

!pip install onnx==1.6.0 onnx-tf==1.5.0 !pip install tensorflow-gpu==1.15.0

Cloned your repository

!git clone https://github.com/zldrobit/onnx_tflite_yolov3

Uploaded YOLOv3 .cfg and .weights files and changed the directory to onnx_tflite_yolov3 folder

And then, when I ran this command on Colab:

!python3 detect.py --cfg cfg/yolov3-counter_detection.cfg --weights weights/yolov3_counter_detection.weights

The error occurred during its execution.

[zldrobit]

Here's my notebook (https://colab.research.google.com/drive/1Cm3sQXoBMOnCFYNNKqAS-5eqJdlj8gV5?usp=sharing) to reproduce the python3 detect.py xxxxxxx procedure. This notebook runs without any error. You could compare your notebook with this one to find out the cause of the problem.

[zldrobit]

I close this issue since there is no recent activity.

[jpacifico]

Hi, facing same problem converting my yolov3 darknet model. Exactly the same error message with your colab notebook. This error does not occur with the base yolov3 weights but with a custom single-class model. @zldrobit any idea ? @shreyapamecha did you solve it ?

File "/content/drive/My Drive/onnx_tflite_yolov3/models.py", line 203, in forward p_cls = torch.cat(p_cls0, io[..., 6:], -1) TypeError: cat() received an invalid combination of arguments - got (int, Tensor, int), but expected one of:

• (tuple of Tensors tensors, name dim, Tensor out) didn't match because some of the arguments have invalid types: (int, Tensor, int)
• (tuple of Tensors tensors, int dim, Tensor out) didn't match because some of the arguments have invalid types: (int, Tensor, int)