# Error loading cityscape dataset

**URL:** <https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488>\
**Category:** Uncategorized\
**Created:** [October 30, 2021, 2:53pm UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488 "2021-10-30T14:53:26Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![xavi0007](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xavi0007/32/43457_2.png) [@xavi0007](https://discuss.pytorch.org/u/xavi0007)\
**Post date:** [October 30, 2021, 2:53pm UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488/1 "2021-10-30T14:53:26Z")

</div>

I am trying to load the cityscape dataset leftimg8bit and gtFine, downloaded from the website.  
I am also using the DataLoader for city scape provided by PyTorch. However, I am getting the error " TypeError: default\_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found  
\<class ‘PIL.PngImagePlugin.PngImageFile’\> " when enumerating the loaded data.

I have also already made sure to use transforms.ToTensor()  
Any idea what I did wrong here?

An excerpt of my code:

```auto
data_transforms_train = transforms.Compose([
        transforms.Resize(256),
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
    ])

    data_transforms_val = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
    ])

    train_dataset = torchvision.datasets.Cityscapes(os.path.join(root_dir, 'data/cityscapes'),
        split='train', mode='fine', target_type='semantic', transform=data_transforms_train)
    val_dataset = torchvision.datasets.Cityscapes(os.path.join(root_dir, 'data/cityscapes'),
        split='val', mode='fine', target_type='semantic', transform=data_transforms_val)

    train_loader = data.DataLoader(
        train_dataset,
        batch_size=batch_size,
        num_workers=num_workers,
        pin_memory=False,
        shuffle=True
    )
    val_loader = data.DataLoader(
        val_dataset,
        batch_size=batch_size,
        num_workers=num_workers,
        pin_memory=True,
        shuffle=False
    )

```

> Blockquote  
> Traceback (most recent call last):  
> File “/Users/xavier/Programming/FishNet/main\_semantic\_segmentation.py”, line 271, in   
> main()  
> File “/Users/xavier/Programming/FishNet/main\_semantic\_segmentation.py”, line 259, in main  
> train(train\_loader, model, criterion, optimizer, epoch)  
> File “/Users/xavier/Programming/FishNet/main\_semantic\_segmentation.py”, line 99, in train  
> for i, data in enumerate(train\_loader):  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/dataloader.py”, line 521, in **next**  
> data = self.\_next\_data()  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/dataloader.py”, line 1203, in \_next\_data  
> return self.\_process\_data(data)  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/dataloader.py”, line 1229, in \_process\_data  
> data.reraise()  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/\_utils.py”, line 425, in reraise  
> raise self.exc\_type(msg)  
> TypeError: Caught TypeError in DataLoader worker process 0.  
> Original Traceback (most recent call last):  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/\_utils/worker.py”, line 287, in \_worker\_loop  
> data = fetcher.fetch(index)  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/\_utils/fetch.py”, line 47, in fetch  
> return self.collate\_fn(data)  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/\_utils/collate.py”, line 84, in default\_collate  
> return [default\_collate(samples) for samples in transposed]  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/\_utils/collate.py”, line 84, in   
> return [default\_collate(samples) for samples in transposed]  
> File “/Users/xavier/miniforge3/lib/python3.9/site-packages/torch/utils/data/\_utils/collate.py”, line 86, in default\_collate  
> raise TypeError(default\_collate\_err\_msg\_format.format(elem\_type))  
> TypeError: default\_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found \<class ‘PIL.PngImagePlugin.PngImageFile’\>

Thanks!

---

<div class="post-metadata">

**Author:** ![techkang](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/techkang/32/43474_2.png) [@techkang](https://discuss.pytorch.org/u/techkang)\
**Post date:** [October 31, 2021, 2:53am UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488/2 "2021-10-31T02:53:00Z")

</div>

It is wired. I think you can try `print(train_dataset[0])` to varify the output of your dataset.

---

<div class="post-metadata">

**Author:** ![xavi0007](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xavi0007/32/43457_2.png) [@xavi0007](https://discuss.pytorch.org/u/xavi0007)\
**Post date:** [October 31, 2021, 5:46am UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488/3 "2021-10-31T05:46:47Z")

</div>

it prints out

```auto
(tensor([[[-1.0733, -1.0733, -1.0904, ..., -0.9363, -0.3883, -0.3883],
         [-1.0733, -1.0904, -1.0904, ..., -0.8678, -0.3541, -0.3541],
         [-1.0904, -1.0904, -1.0904, ..., -0.8164, -0.2684, -0.2856],
         ...,
         [-0.6623, -1.0048, -0.9192, ..., -0.5424, -0.6965, -0.6965],
         [-0.6109, -0.9363, -1.0562, ..., -0.5938, -0.7650, -0.8849],
         [-0.5424, -0.8164, -1.1247, ..., -0.7993, -0.8164, -0.8507]],

        [[-0.6352, -0.6527, -0.6527, ..., -0.6877, -0.1450, -0.1099],
         [-0.6527, -0.6702, -0.6527, ..., -0.6176, -0.0924, -0.0749],
         [-0.6527, -0.6527, -0.6702, ..., -0.5651, -0.0224, -0.0049],
         ...,
         [-0.3025, -0.6702, -0.6702, ..., -0.2850, -0.4426, -0.4426],
         [-0.2850, -0.6001, -0.8102, ..., -0.3375, -0.4951, -0.6001],
         [-0.2325, -0.4776, -0.8627, ..., -0.5476, -0.5826, -0.6001]],

        [[-0.4450, -0.4275, -0.4450, ..., -0.6541, -0.1312, -0.0441],
         [-0.4450, -0.4450, -0.4624, ..., -0.6018, -0.0441, 0.0605],
         [-0.4450, -0.4624, -0.4624, ..., -0.5495, 0.0256, 0.1651],
         ...,
         [-0.3927, -0.6890, -0.6715, ..., -0.3927, -0.4973, -0.4973],
         [-0.3578, -0.6193, -0.7761, ..., -0.4450, -0.5670, -0.6018],
         [-0.3404, -0.5495, -0.8284, ..., -0.5670, -0.5844, -0.6018]]]), <PIL.PngImagePlugin.PngImageFile image mode=L size=2048x1024 at 0x12958A790>)

```

---

<div class="post-metadata">

**Author:** ![eqy](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/eqy/32/46233_2.png) [@eqy](https://discuss.pytorch.org/u/eqy)\
**Post date:** [October 31, 2021, 6:55am UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488/4 "2021-10-31T06:55:36Z")

</div>

That error does look strange, could you post how you are iterating over the dataloader? I think just a little additional code would be enough to potentially reproduce the issue.

---

<div class="post-metadata">

**Author:** ![xavi0007](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xavi0007/32/43457_2.png) [@xavi0007](https://discuss.pytorch.org/u/xavi0007)\
**Post date:** [October 31, 2021, 7:07am UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488/5 "2021-10-31T07:07:59Z")

</div>

My entire training code would be like so

```auto
def train(train_loader, model, criterion, optimizer, epoch):
    train_loss = AverageMeter()
    model.train()

    for i, (inputs, labels) in enumerate(train_loader):
     
        
        N = inputs.size(0)
        inputs = torch.FloatTensor(inputs).to(device)
        labels = torch.LongTensor(labels).to(device)

        optimizer.zero_grad()
        outputs = model(inputs)

        loss = criterion(outputs, labels.to(device)) / N
        loss.backward()
        optimizer.step()

        train_loss.update(loss.data[0], N)

    

```

---

<div class="post-metadata">

**Author:** ![techkang](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/techkang/32/43474_2.png) [@techkang](https://discuss.pytorch.org/u/techkang)\
**Post date:** [October 31, 2021, 7:17am UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488/6 "2021-10-31T07:17:51Z")

</div>

> [@xavi0007](#):
>
> it prints out

It is clearly that this default dataset return the input tensor and semenstic labels, but the labels is a PIL Image.

You can write your own dataset to process the PIL Image. For example:

```auto
class MyCitySpace(torchvision.datasets.Cityspaces):
    def __getitem__ (self, item):
        inputs, target = super(). __getitem__ (item)
        return inputs, np.array(target)

```

---

<div class="post-metadata">

**Author:** ![xavi0007](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xavi0007/32/43457_2.png) [@xavi0007](https://discuss.pytorch.org/u/xavi0007)\
**Post date:** [October 31, 2021, 12:40pm UTC](https://discuss.pytorch.org/t/error-loading-cityscape-dataset/135488/7 "2021-10-31T12:40:51Z")

</div>

Thanks! that works, additionally I also changed it data type to long using target.astype(np.long) due to requirements of PyTorch.