/usr/local/lib/python3.8/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead.
warnings.warn(
/usr/local/lib/python3.8/dist-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing weights=ResNet50_Weights.IMAGENET1K_V1. You can also use weights=ResNet50_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
Create new model
=> init weights
Adjusting learning rate of group 0 to 1.0000e-03.
loading annotations into memory...
Done (t=1.28s)
creating index...
index created!
############# Starting Epoch 0 | LR: 0.001 #############
0%| | 0/525 [00:02<?, ?it/s]
Traceback (most recent call last):
File "./train.py", line 348, in
main()
File "./train.py", line 295, in main
loss, miou = train(opt, train_loader, m, criterion, optimizer, writer)
File "./train.py", line 106, in train
debug_writing(writer, output, labels, inps, opt.trainIters)
File "/tmp/alphapose/utils/logger.py", line 26, in debug_writing
tmp_inp[0] += torch.sum(F.interpolate(tmp_tar, scale_factor=4, mode='bilinear'), dim=0)[0]
File "/usr/local/lib/python3.8/dist-packages/torch/nn/functional.py", line 3961, in interpolate
raise NotImplementedError(
NotImplementedError: Input Error: Only 3D, 4D and 5D input Tensors supported (got 2D) for the modes: nearest | linear | bilinear | bicubic | trilinear | area | nearest-exact (got bilinear)
你好,在训练singlehand时加上--debug报下面错误,不加可以正常训练:
/usr/local/lib/python3.8/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /usr/local/lib/python3.8/dist-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or
main()
File "./train.py", line 295, in main
loss, miou = train(opt, train_loader, m, criterion, optimizer, writer)
File "./train.py", line 106, in train
debug_writing(writer, output, labels, inps, opt.trainIters)
File "/tmp/alphapose/utils/logger.py", line 26, in debug_writing
tmp_inp[0] += torch.sum(F.interpolate(tmp_tar, scale_factor=4, mode='bilinear'), dim=0)[0]
File "/usr/local/lib/python3.8/dist-packages/torch/nn/functional.py", line 3961, in interpolate
raise NotImplementedError(
NotImplementedError: Input Error: Only 3D, 4D and 5D input Tensors supported (got 2D) for the modes: nearest | linear | bilinear | bicubic | trilinear | area | nearest-exact (got bilinear)
None
for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passingweights=ResNet50_Weights.IMAGENET1K_V1
. You can also useweights=ResNet50_Weights.DEFAULT
to get the most up-to-date weights. warnings.warn(msg) Create new model => init weights Adjusting learning rate of group 0 to 1.0000e-03. loading annotations into memory... Done (t=1.28s) creating index... index created! ############# Starting Epoch 0 | LR: 0.001 ############# 0%| | 0/525 [00:02<?, ?it/s] Traceback (most recent call last): File "./train.py", line 348, in