PyTorch_YOLOv4
PyTorch_YOLOv4 copied to clipboard
WongKinYiu
Pytorch 1.8: Tensor to cumpy
Hi, I am using pytorch 1.8 with cuda 11.2. While training on coco or custom dataset I get this error message. I used pretained weight yolov4.conv.137.pth to train the custom dataset. Does anybody has the same problem and fixed it?
Traceback (most recent call last):
File "train.py", line 438, in <module>
train(hyp, opt, device, tb_writer)
File "train.py", line 301, in train
results, maps, times = test.test(opt.data,
File "/home/kamal/Documents/PyTorch_YOLOv4/test.py", line 206, in test
plot_images(img, output_to_target(output, width, height), paths, str(f), names) # predictions
File "/home/kamal/Documents/PyTorch_YOLOv4/utils/general.py", line 907, in output_to_target
return np.array(targets)
File "/home/kamal/.virtualenvs/pytorch-yolov4/lib/python3.8/site-packages/torch/tensor.py", line 621, in __array__
return self.numpy()
TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
Yes，I have the same problem in pytorch1.7.1 with cuda 10.2.I also want the solutions.
Yes，I have the same problem in pytorch1.7.1 with cuda 10.2.I also want the solutions.
@Arthur-zfc were you able to fix it?
我是用的是单机8卡，在general.py的output_to_target方法中 将这两句注释if isinstance(output, torch.Tensor): output = output.cpu().numpy() 并加上 output = [temp.cpu().numpy() for temp in output]
我是用的是单机8卡，在general.py的output_to_target方法中 将这两句注释if isinstance(output, torch.Tensor): output = output.cpu().numpy() 并加上 output = [temp.cpu().numpy() for temp in output]
Thank you, worked like a charm. But need to output.cpu() >> output in test.py in output_to_target()
我是用的是单机8卡，在general.py的output_to_target方法中 将这两句注释if isinstance(output, torch.Tensor): output = output.cpu().numpy() 并加上 output = [temp.cpu().numpy() for temp in output]
Thank you!
