# DataLoader is not working for labels

**URL:** <https://discuss.pytorch.org/t/dataloader-is-not-working-for-labels/18836>\
**Category:** Uncategorized\
**Created:** [May 29, 2018, 12:46pm UTC](https://discuss.pytorch.org/t/dataloader-is-not-working-for-labels/18836 "2018-05-29T12:46:54Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![saan77](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/saan77/32/3726_2.png) [@saan77](https://discuss.pytorch.org/u/saan77)\
**Post date:** [May 29, 2018, 12:46pm UTC](https://discuss.pytorch.org/t/dataloader-is-not-working-for-labels/18836/1 "2018-05-29T12:46:54Z")

</div>

Hi,

I have written one class to load my custom dataset. The class is as follows:

```auto
class ShapeDataset(Dataset):
	def __init__ (self, root_dir, transform=None):
		self.img_names = glob.glob("training_data/*.jpg")
		self.img_names = [os.path.basename(i) for i in self.img_names]
		self.txt_names = [i[:-4]+'.txt' for i in self.img_names ]
		self.root_dir = root_dir
		self.labels = generate_labels(self.txt_names, self.root_dir)
		self.transform = transform

	def __getitem__ (self, index):
		self.img_name = os.path.join(self.root_dir, self.img_names[index])
		self.image = Image.open(self.img_name)
		self.label = self.labels[index]
		if self.transform:
			self.image = self.transform(self.image)

		return (self.image, self.label)

	def __len__ (self,):
		return len(self.img_names)

```

I tested it to make sure it is working:

```auto
ata = ShapeDataset("training_data")
img, l = data. __getitem__ (1347)
print(l) #output [2, 2, 1]
img.show()

```

Here, the label is a list of 3 elements. Everything worked fine until I used DataLoader as follows and tried to see some data.

```auto
data = dataset.ShapeDataset("training_data", transform=transforms.Compose([transforms.ToTensor()]))
dataset_loader = torch.utils.data.DataLoader(dataset=data, batch_size=10, shuffle=False)

for batch_idx, (data, target) in enumerate(dataset_loader):
	print(target)

```

In each iteration, the target should be a list of 10 lists. But I get something like this:

```auto
[('1', '1', '0', '3', '2', '1', '1', '2', '2', '2'), ('2', '0', '3', '1', '3', '1', '4', '1', '2', '3'), ('2', '0', '0', '1', '0', '1', '2', '1', '1', '1')]

```

Clearly, this is not the expected output. I don’t understand what went wrong. However, it is working fine for the images. In each iteration, it returns a matrix of size 10 \* 3 \* height \* width. There is something wrong with labels. Any help will be appreciated.

Note: Generate\_labels function does some preprocessing to get the labels in proper form. I think it does not matter because **getitem** returns label in expected dimensions (list of 3 elements).

Thanks

---

<div class="post-metadata">

**Author:** ![Sfitsos](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sfitsos/32/10434_2.png) [@Sfitsos](https://discuss.pytorch.org/u/Sfitsos)\
**Post date:** [May 29, 2018, 1:06pm UTC](https://discuss.pytorch.org/t/dataloader-is-not-working-for-labels/18836/2 "2018-05-29T13:06:48Z")

</div>

I think that the dataloader will fetch samples(which are tensors) in a batch and put them in a tensor with the first dimension being the batch size. If you want to get a list of lists then you probably need to make your own collate function.  
If you don’t care about having a list of lists then you can put the labels in a tensor. For example, wrapping your list in a tensor will work so instead of this:

```
def __getitem__ (self, index):
    return [1.0, 2.0, 3.0]

```

you can use **this** :

```
def __getitem__ (self, index):
    return torch.FloatTensor([1.0, 2.0, 3.0])

```

If you want to see how to make your own collate function then look here:

> [@How to create a dataloader with variable-size input](https://discuss.pytorch.org/t/how-to-create-a-dataloader-with-variable-size-input/8278/2):
>
> you need to write a custom collate\_fn and pass it to your data loader. [Questions about Dataloader and Dataset](https://discuss.pytorch.org/t/questions-about-dataloader-and-dataset/806/2)