pytorch1.7 is not completely support.'inplace'! 'inplace'! 'inplace'!

[cww97]

Before submitting a bug report, please be aware that your issue must be reproducible with all of the following, otherwise it is non-actionable, and we can not help you:

• Current repo: run git fetch && git status -uno to check and git pull to update repo
• Common dataset: coco.yaml or coco128.yaml
• Common environment: Colab, Google Cloud, or Docker image. See https://github.com/ultralytics/yolov5#environments

If this is a custom dataset/training question you must include your train*.jpg, test*.jpg and results.png figures, or we can not help you. You can generate these with utils.plot_results().

🐛 Bug

A clear and concise description of what the bug is.

your requirements.txt said pytorch>=1.7, on cpu this is fine, but when I ran it on GPU, yeah, boom
I fixed it from [here](https://github.com/ultralytics/yolov5/issues/1265#issuecomment-723497340),
yes, downgrade pytorch into 1.6.

To Reproduce (REQUIRED)

Input:

$ python detect.py --source ./inference/images/ --weights yolov5s.pt --conf 0.4

Output:

Traceback (most recent call last):
  File "detect.py", line 188, in <module>
    detect()
  File "detect.py", line 69, in detect
    _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once
  File "/opt/chenweiwen/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/chenweiwen/sec-model-code/yolov5/models/yolo.py", line 112, in forward
    return self.forward_once(x, profile)  # single-scale inference, train
  File "/opt/chenweiwen/sec-model-code/yolov5/models/yolo.py", line 132, in forward_once
    x = m(x)  # run
  File "/opt/chenweiwen/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/chenweiwen/sec-model-code/yolov5/models/common.py", line 88, in forward
    return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
  File "/opt/chenweiwen/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/chenweiwen/sec-model-code/yolov5/models/common.py", line 32, in fuseforward
    return self.act(self.conv(x))
  File "/opt/chenweiwen/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/chenweiwen/anaconda3/lib/python3.7/site-packages/torch/nn/modules/activation.py", line 438, in forward
    return F.hardswish(input, self.inplace)
  File "/opt/chenweiwen/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 779, in __getattr__
    type(self).__name__, name))
torch.nn.modules.module.ModuleAttributeError: 'Hardswish' object has no attribute 'inplace'

Expected behavior

A clear and concise description of what you expected to happen.

Environment

If applicable, add screenshots to help explain your problem.

• OS: [centOS 7]
• GPU [Tesla M60]

Additional context

Add any other context about the problem here.

[github-actions]

👋 Hello @cww97, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

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 training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

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

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@cww97 our Colab notebook runs 1.7.0 on GPU perfectly well. Everything is working correctly on all OSs if you meet the requirements.

[wwdok]

You don't have to downgrade torch version, just refer to this, it works for me !