Facing problem while converting Darknet weights to ONNX model for YOLOv3 about onnx_tflite_yolov3 HOT 5 CLOSED

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

from onnx_tflite_yolov3.

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.

from onnx_tflite_yolov3.

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.

from onnx_tflite_yolov3.

I close this issue since there is no recent activity.

from onnx_tflite_yolov3.

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)

from onnx_tflite_yolov3.