torch 1.4 error - RuntimeError: Failed to register operator torchvision::_new_empty_tensor_op.

[ChargedMonk]

The latest commit in the requirements.txt stating support for torch 1.4 gives the following error when detect.py is run

File "detect.py", line 3, in <module>
   from utils.datasets import *
 File "/content/drive/My Drive/SocialDistancing/yolov5/utils/datasets.py", line 17, in <module>
   from utils.utils import xyxy2xywh, xywh2xyxy
 File "/content/drive/My Drive/SocialDistancing/yolov5/utils/utils.py", line 18, in <module>
   import torchvision
 File "/usr/local/lib/python3.6/dist-packages/torchvision/__init__.py", line 3, in <module>
   from torchvision import models
 File "/usr/local/lib/python3.6/dist-packages/torchvision/models/__init__.py", line 12, in <module>
   from . import detection
 File "/usr/local/lib/python3.6/dist-packages/torchvision/models/detection/__init__.py", line 1, in <module>
   from .faster_rcnn import *
 File "/usr/local/lib/python3.6/dist-packages/torchvision/models/detection/faster_rcnn.py", line 7, in <module>
   from torchvision.ops import misc as misc_nn_ops
 File "/usr/local/lib/python3.6/dist-packages/torchvision/ops/__init__.py", line 13, in <module>
   _register_custom_op()
 File "/usr/local/lib/python3.6/dist-packages/torchvision/ops/_register_onnx_ops.py", line 51, in _register_custom_op
   register_custom_op_symbolic('torchvision::_new_empty_tensor_op', new_empty_tensor_op, _onnx_opset_version)
 File "/usr/local/lib/python3.6/dist-packages/torch/onnx/__init__.py", line 200, in register_custom_op_symbolic
   return utils.register_custom_op_symbolic(symbolic_name, symbolic_fn, opset_version)
 File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 793, in register_custom_op_symbolic
   .format(symbolic_name))
RuntimeError: Failed to register operator torchvision::_new_empty_tensor_op. The symbolic name must match the format Domain::Name, and sould start with a letter and contain only                            alphanumerical charactersrwise it is non-actionable, and we can not help you:

[github-actions]

Hello @ChargedMonk, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@ChargedMonk yes I see this also. We pushed a commit today to allow torch>=1.4
24dd150

But perhaps this was a bad decision. I will revert this to the original torch>=1.5 requirement.

[glenn-jocher]

@Lornatang I think the recent PR #143 may not work correctly. See @ChargedMonk's issue above.

[Lornatang]

@glenn-jocher I tried it on this machine and found no errors.
I hope you keep that comment, because this problem is indeed encountered by many people, as for @ChargedMonk the error encountered, I may need some time to reproduce his error and improve it.

[Lornatang]

@glenn-jocher @ChargedMonk This failed It is because of the mismatch of torchvision, I will add a PR to ensure that the Torch and Torchvision versions correspond. it's my mistake.

More details see: pytorch/vision#1827 and pytorch/vision#1827 (comment)

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.