search

paultsw / nice_pytorch

Nonlinear Independent Components Estimation (Dinh et al, 2014) in PyTorch.
BSD 3-Clause "New" or "Revised" License
115 stars 24 forks source link

Train.py for Cifar-10 Error -- RuntimeError: Dimension out of range ( #3

Open bryansosa opened 5 years ago

bryansosa commented 5 years ago

I am getting the error described below when runing train.py for cifar-10. Note that I previously run make_datasets.py

$ python train.py --dataset=cifar10 Epoch 0: 0%| | 0/3125 [00:00<?, ?it/s]Traceback (most recent call last): File "train.py", line 256, in <module> model = train(args) File "train.py", line 174, in train for inputs, _ in tqdm(dataloader): File "/home/exx/anaconda3/lib/python3.7/site-packages/tqdm/_tqdm.py", line 1022, in __iter__ for obj in iterable: File "/home/exx/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 615, in __next__ batch = self.collate_fn([self.dataset[i] for i in indices]) File "/home/exx/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 615, in <listcomp> batch = self.collate_fn([self.dataset[i] for i in indices]) File "/home/exx/anaconda3/lib/python3.7/site-packages/torchvision/datasets/cifar.py", line 124, in __getitem__ img = self.transform(img) File "/home/exx/anaconda3/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 60, in __call__ img = t(img) File "/home/exx/anaconda3/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 736, in __call__ if tensor.size(0) * tensor.size(1) * tensor.size(2) != self.transformation_matrix.size(0): RuntimeError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

TiJoy commented 4 years ago

I got this error too, did you solve it?

datduong commented 3 years ago

It looks like the input tensor (the image) has to be in shape channel x width x height. However, this code may take only grayscale images (so just 1 channel).