Pytorch-cyclegan-and-pix2pix: Question: Regarding the unsupported operand type error

[TheIllusion]

Hi.
I've been using the torch based CycleGAN and Pix2pix code for a while and I think it's a great work.
The paper is also astonishing.

Now I want to move to the PyTorch based CycleGan/Pix2pix code.
But I have an error in my environment.

My environment is
-Ubuntu 14.04
-Python 2.7
-CUDA 8

and the error message is attached below.

As far as I remember the PyTorch based code worked OK in my environment.
I guess this problem might be caused by my environment settings and it might be fixed easily.
But I don't have any clue to fix this.

Could you give any tips for this issue?

< Error message>

### python train.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan

...
...
...
model [CycleGANModel] was created
create web directory ./checkpoints/maps_cyclegan/web...
Traceback (most recent call last):
File "train.py", line 20, in
for i, data in enumerate(dataset):
File "/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py", line 212, in __next__
return self._process_next_batch(batch)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py", line 239, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
TypeError: Traceback (most recent call last):
File "/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py", line 41, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/media/illusion/ML_DATA_SSD_M550/pytorch-CycleGAN-and-pix2pix/data/unaligned_dataset.py", line 46, in __getitem__
A_img = self.transform(A_img)
File "/usr/local/lib/python2.7/dist-packages/torchvision/transforms.py", line 29, in __call__
img = t(img)
File "/usr/local/lib/python2.7/dist-packages/torchvision/transforms.py", line 139, in __call__
ow = int(self.size * w / h)

TypeError: unsupported operand type(s) for /: 'list' and 'int'

[kabrio]

maxbe you are not using the right version of torchvision?

try pip install https://github.com/pytorch/vision/archive/master.zip --upgrade

[junyanz]

Thanks @kabrio. It should work.
To use our latest dataset loader, you need to install the latest PyTorch vision library.
bash git clone https://github.com/pytorch/vision cd vision python setup.py install

[TheIllusion]

Thanks @kabrio and @junyanz.
Great. It works!

[aestebanlansaque]

I have the same problem but i got this message when I tried to download pyTorch:

pip install http://download.pytorch.org/whl/cu80/torch-0.1.12.post2-cp27-none-linux_x86_64.whl --user
Requirement already satisfied: torch==0.1.12.post2 from http://download.pytorch.org/whl/cu80/torch-0.1.12.post2-cp27-none-linux_x86_64.whl in /usr/local/lib/python2.7/dist-packages
Requirement already satisfied: pyyaml in /usr/local/lib/python2.7/dist-packages (from torch==0.1.12.post2)

It looks like I have the last pyTorch version but Is till get the same error. Did you guys soleved just by installing the last pyTorch version?

[junyanz]

You need to install the latest torch vision library from the source.

git clone https://github.com/pytorch/vision
cd vision
python setup.py install