Hello,
I have created a Class for the Dataset, (Code Below)
`Preformatted text`class CustomDataset(Dataset):
def __init__(self, csv_file, id_col, target_col, root_dir, sufix=None, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
id_col (string): csv id column name.
target_col (string): csv target column name.
sufix (string, optional): Optional sufix for samples.
transform (callable, optional): Optional transform to be applied on a sample.
"""
self.data = pd.read_csv(csv_file)
self.id = id_col
self.target = target_col
self.root = root_dir
self.sufix = sufix
self.transform = transform
def __len__(self):
return len(self.data)
def __getitem__(self, idx):
# get the image name at the different idx
img_name = self.data.loc[idx, self.id]
# if there is not sufic, nothing happened. in this case sufix is '.jpg'
if self.sufix is not None:
img_name = img_name + self.sufix
# it opens the image of the img_name at the specific idx
image = Image.open(os.path.join(self.root, img_name))
# if there is not transform nothing happens, here we defined below two transforms for train and for test
if self.transform is not None:
image = self.transform(image)
# define the label based on the idx
label = pd.read_csv(csv_file).loc[idx, ['healthy', 'multiple_diseases', 'rust', 'scab']].values
label = torch.from_numpy(label.astype(np.int8))
#label = label.unsqueeze(-1)
return image, label
It returns a label shape: torch.size([4])
and then
train_dataset = CustomDataset(csv_file=data_dir+'train.csv', root_dir=data_dir+'images', **params)
train_loader = DataLoader(train_dataset, batch_size=4, shuffle=True, num_workers=4)
But I have this message Error:" ValueError: Expected input batch_size (4) to match target batch_size (16)."
for idx, (data, target) in enumerate(loaders):
## find the loss and update the model parameters accordingly
## record the average training loss, using something like
## train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
optimizer.zero_grad()
# forward pass: compute predicted outputs by passing inputs to the model
#print(data)
output = model(data)
# calculate the batch loss
#torch.max(target, 1)[1]
print('output shape: ', output.shape)
#target = target.view(-1)
print('target shape: ', target.shape)
loss = criterion(output, target)
I can see that the
- Output shape is: torch.size([4, 133])
- Target shape is: torch.size([4, 4])
I know that my target should be ([4]) and as the label shape of the dataset is this shape I don’t understand why it changed to [(4, 4)]).
I don’t understand what I missed and how can I get the target shape to be ([4])
Look forward to reading your clarifications
