Hello, I’m a beginner to PyTorch, and I don’t understand why I’m getting the error in the title when I declare images, labels = dataiter.next(). Below is everything relevant
class DogsDataset(Dataset):
def __init__(self, df_data, data_dir = './', transform=None):
super().__init__()
self.df = df_data.values
self.data_dir = data_dir
# self.img_ext = img_ext
self.transform = transform
def __len__(self):
return len(self.df)
def __getitem__(self, index):
img_name,label = self.df[index]
img_path = os.path.join(self.data_dir, img_name)
image = cv2.imread(img_path)
if self.transform is not None:
image = self.transform(image)
return image, label
data_transform = transforms.Compose([
transforms.ToPILImage(),
transforms.RandomHorizontalFlip(),
transforms.Resize(32),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])])
#added
df_labels = pd.read_csv(LABELS_CSV_PATH)
train_data = DogsDataset(df_data=df_labels, data_dir=TRAIN_IMG_PATH, transform=data_transform)
# Set Batch Size
batch_size = 64
# Percentage of training set to use as validation
valid_size = 0.2
# obtain training indices that will be used for validation
num_train = len(train_data)
indices = list(range(num_train))
np.random.shuffle(indices)
split = int(np.floor(valid_size * num_train))
train_idx, valid_idx = indices[split:], indices[:split]
# Create Samplers
train_sampler = SubsetRandomSampler(train_idx)
valid_sampler = SubsetRandomSampler(valid_idx)
# prepare data loaders (combine dataset and sampler)
train_loader = DataLoader(train_data, batch_size=batch_size, sampler=train_sampler)
valid_loader = DataLoader(train_data, batch_size=batch_size, sampler=valid_sampler)
dataiter = iter(train_loader)
images, labels = dataiter.next()
TypeError Traceback (most recent call last)
<ipython-input-10-a3862cdf9037> in <module>
1 # obtain one batch of training images
2 dataiter = iter(train_loader)
----> 3 images, labels = dataiter.next()
4 print(images)
/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py in __next__(self)
558 if self.num_workers == 0: # same-process loading
559 indices = next(self.sample_iter) # may raise StopIteration
--> 560 batch = self.collate_fn([self.dataset[i] for i in indices])
561 if self.pin_memory:
562 batch = _utils.pin_memory.pin_memory_batch(batch)
/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py in <listcomp>(.0)
558 if self.num_workers == 0: # same-process loading
559 indices = next(self.sample_iter) # may raise StopIteration
--> 560 batch = self.collate_fn([self.dataset[i] for i in indices])
561 if self.pin_memory:
562 batch = _utils.pin_memory.pin_memory_batch(batch)
<ipython-input-6-ee5990aa6797> in __getitem__(self, index)
16 image = cv2.imread(img_path)
17 if self.transform is not None:
---> 18 image = self.transform(image)
19 return image, label
/opt/conda/lib/python3.6/site-packages/torchvision/transforms/transforms.py in __call__(self, img)
59 def __call__(self, img):
60 for t in self.transforms:
---> 61 img = t(img)
62 return img
63
/opt/conda/lib/python3.6/site-packages/torchvision/transforms/transforms.py in __call__(self, pic)
125
126 """
--> 127 return F.to_pil_image(pic, self.mode)
128
129 def __repr__(self):
/opt/conda/lib/python3.6/site-packages/torchvision/transforms/functional.py in to_pil_image(pic, mode)
110 """
111 if not(isinstance(pic, torch.Tensor) or isinstance(pic, np.ndarray)):
--> 112 raise TypeError('pic should be Tensor or ndarray. Got {}.'.format(type(pic)))
113
114 elif isinstance(pic, torch.Tensor):
TypeError: pic should be Tensor or ndarray. Got <class 'NoneType'>.