# pytorch0.4.0 torchsample0.1.3
get error:
Traceback (most recent call last):
File "main.py", line 383, in
train(data_loader, model, criterion, optimizer, scheduler, epoch)
File "main.py", line 132, in train
for i, (input, target) in enumerate(train_loader):
File "/home/user/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 286, in next
return self._process_next_batch(batch)
File "/home/user/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 307, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/home/user/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/user/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "main.py", line 42, in getitem
data, target = transform_sample(data, target)
File "main.py", line 112, in transform_sample
im = rand_affine(im)
File "/home/user/anaconda3/lib/python3.6/site-packages/torchsample/transforms/affine_transforms.py", line 92, in call
interp=self.interp)(*inputs)
File "/home/user/anaconda3/lib/python3.6/site-packages/torchsample/transforms/affine_transforms.py", line 130, in call
mode=interp[idx])
File "/home/user/anaconda3/lib/python3.6/site-packages/torchsample/utils.py", line 129, in th_affine2d
x_transformed = th_nearest_interp2d(x.contiguous(), new_coords)
File "/home/user/anaconda3/lib/python3.6/site-packages/torchsample/utils.py", line 145, in th_nearest_interp2d
x_ix = x.mul(stride[1]).long()
RuntimeError: Expected object of type torch.FloatTensor but found type torch.LongTensor for argument #2 'other'
torchsample has not been updated for nearly half year, I think it's quite hard for the current master branch version to be compatible with changes in pytorch 0.4.0
I make my own forked version of torchsample and I'm still testing it on pytorch 0.4.0, maybe you can make your own torchsample until ncullen93 begin updateing again
nitrain
