I have image dataset that is in .mat format. But when I use my dataloader, I get the following error:
Traceback (most recent call last):
File "vanilla_triplet_vae.py", line 808, in <module>
main()
File "vanilla_triplet_vae.py", line 779, in main
train(train_loader, tnet,decoder,descriptor, criterion, optimizer, epoch)
File "vanilla_triplet_vae.py", line 418, in train
for batch_idx, (data1, data2, data3) in enumerate(train_loader):
File "/home/hmishfaq/anaconda2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 201, in __next__
return self._process_next_batch(batch)
File "/home/hmishfaq/anaconda2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 221, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
TypeError: Traceback (most recent call last):
File "/home/hmishfaq/anaconda2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 40, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/hmishfaq/anaconda2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 112, in default_collate
.format(type(batch[0]))))
TypeError: batch must contain tensors, numbers, dicts or lists; found <type 'NoneType'>
My dataloader code is this:
from PIL import Image
import os
import os.path
import torch.utils.data
import torchvision.transforms as transforms
import numpy as np
import scipy.io as sio
import torch
filenames = {'train': ['triplet_train.csv'],
'val': ['triplet_val.csv'],
'test': ['triplet_test.csv']}
def default_image_loader(path):
data = sio.loadmat(path) #example path /data/p110.mat
return data['NormImg']
# return Image.open(path).convert('RGB')
class TripletImageLoader(torch.utils.data.Dataset):
def __init__(self, root, base_path, filenames_filename, split, n_triplets, transform=None,
loader=default_image_loader):
""" filenames_filename: A text file with each line containing the path to an image e.g.,
images/class1/sample.mat
triplets_file_name: A text file with each line containing three integers,
where integer i refers to the i-th image in the filenames file.
For a line of intergers 'a b c', a triplet is defined such that image a is more
similar to image c than it is to image b, e.g.,
0 2017 42 """
self.root = root
self.base_path = base_path
self.filenamelist = []
print(os.path.join(self.root, filenames_filename))
for line in open(os.path.join(self.root, filenames_filename)):
self.filenamelist.append(line.rstrip('\n\x00'))
triplets = []
if split == 'train':
fnames = filenames['train']
elif split == 'val':
fnames = filenames['val']
else:
fnames = filenames['test']
for line in open(os.path.join(self.root, split, fnames[0])):
triplets.append((line.split(',')[0], line.split(',')[1], line.split(',')[2])) # anchor, far, close
np.random.shuffle(triplets)
self.triplets = triplets[:int(n_triplets)]
self.transform = transform
self.loader = loader
def __getitem__(self, index):
path1, path2, path3 = self.triplets[index]
if os.path.exists(os.path.join('..', self.filenamelist[int(path1)])) and os.path.exists(os.path.join('..', self.filenamelist[int(path2)])) and os.path.exists(os.path.join('..', self.filenamelist[int(path3)])):
img1 = self.loader(os.path.join('..', self.filenamelist[int(path1)]))
img2 = self.loader(os.path.join('..', self.filenamelist[int(path2)]))
img3 = self.loader(os.path.join('..', self.filenamelist[int(path3)]))
img1 = Image.fromarray(img1) #torch.from_numpy(img1)
img2 = Image.fromarray(img2) #torch.from_numpy(img2)
img3 = Image.fromarray(img3) #torch.from_numpy(img3)
if self.transform is not None:
img1 = self.transform(img1)
img2 = self.transform(img2)
img3 = self.transform(img3)
return img1, img2, img3
else:
return None
def __len__(self):
return len(self.triplets)
Not sure where the error is coming from. I used the exact same dataloader for jpeg format images and it was working fine.