Yolov5: No module named 'models' question

[ioir123ju]

🐛 Bug

When I use yolov5 outside the repo and use "torch.load(the_mode, PATH)", I got the error "No module named 'models'"

I see a solution in #22.

But I got error when I use model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)

torch.nn.modules.module.ModuleAttributeError: 'BatchNorm2d' object has no attribute '_non_persistent_buffers_set'

So I still want to load model in this way:
model.load_state_dict(torch.load(new_weights))
Can you tell me how to use model.load_state_dict ?

[github-actions[bot]]

Hello @ioir123ju, 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]

@ioir123ju use Torch Hub. See https://github.com/ultralytics/yolov5/issues/36

[ioir123ju]

Sorry, It doesn't solve my problem.

environment

pytorch 1.6

[glenn-jocher]

@ioir123ju use a working environment. See https://github.com/ultralytics/yolov5#reproduce-our-environment

[ioir123ju]

yes, My environment meets your requirements.

torch 1.6 >= torch1.5
python 3.7

And I can run detect.py in your repo.
But can't load weight in my project.

[glenn-jocher]

@ioir123ju debug your environment, or just use one of our working ones. That's what they are there for.

[rxchen]

I have the same problem, torch 1.6rc2
File "detect.py", line 23, in detect
model = attempt_load(weights, map_location=device) # load FP32 model
File "/home/ruichen/nvme/gitrepo/yolov5/models/experimental.py", line 133, in attempt_load
model.append(torch.load(w, map_location=map_location)['model'].float().fuse().eval()) # load FP32 model
File "/home/ruichen/nvme/gitrepo/yolov5/models/yolo.py", line 149, in fuse
m.conv = torch_utils.fuse_conv_and_bn(m.conv, m.bn) # update conv
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 802, in __setattr__
remove_from(self.__dict__, self._parameters, self._buffers, self._non_persistent_buffers_set)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 772, in __getattr__
type(self).__name__, name))
torch.nn.modules.module.ModuleAttributeError: 'Conv' object has no attribute '_non_persistent_buffers_set'

[fpingham]

Same problem over here.

[glenn-jocher]

@fpingham you are probably using an older version of the repo, an older model, or are not meeting the minimum dependency requirements. I would start from a clean slate in one of the verified environments below.

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab Notebook with free GPU:
• Kaggle Notebook with free GPU: https://www.kaggle.com/ultralytics/yolov5
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Docker Image https://hub.docker.com/r/ultralytics/yolov5. See Docker Quickstart Guide