Can't run with GPU, but worked with CPU

[forallsunday]

Windows 10 , RTX 3080, CUDA 11.0, cudnn 8.04, pytorch 1.7.0
When I typyed "python detect.py --source data/images --weights yolov5s.pt --conf 0.25"
It shows:
RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _thnn_conv2d_forward.

But it was Ok "python detect.py --source data/images --weights yolov5s.pt --conf 0.25 --device CPU"

It seems ocurred in the function "attempt_load".

[github-actions]

Hello @forallsunday, 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.

[JunnYu]

#1447

change line 156

yolov5/utils/torch_utils.py

Lines 153 to 160 in bd29a1c

	try: # FLOPS
	from thop import profile
	stride = int(model.stride.max())
	flops = profile(deepcopy(model), inputs=(torch.zeros(1, 3, stride, stride),), verbose=False)[0] / 1E9 * 2
	img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float
	fs = ', %.1f GFLOPS' % (flops * img_size[0] / stride * img_size[1] / stride) # 640x640 FLOPS
	except (ImportError, Exception):
	fs = ''

flops = profile(deepcopy(model), inputs=(torch.zeros(1, 3, stride, stride).to(next(model.parameters()).device),), verbose=False)[0] / 1E9 * 2

[glenn-jocher]

@JunnYu ah of course. Thanks for spotting this bug! I will take a look at the PR.