Linear probing with imageGPT assertion error when using pixel_values

[kristosh]

I am using code for the linear_probing_with_ImageGPT.ipynb and work with linear probing. I am using python 3.10 with pytorch version 2.6.0 and transformers 4.48.3 and I am using the provided code here:

```
train_ds, test_ds = load_dataset('cifar10', split=['train[:10]', 'test[:10]'])
# split up training into training + validation
splits = train_ds.train_test_split(test_size=0.1)
train_ds = splits['train']
val_ds = splits['test']

dataset = load_dataset('cifar10')
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

feature_extractor = ImageGPTFeatureExtractor.from_pretrained("openai/imagegpt-small")
model = ImageGPTModel.from_pretrained("openai/imagegpt-small")
model.to(device)

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

encoding = feature_extractor(image, return_tensors="pt")
pixel_values = encoding.pixel_values.to(device)
```

I am facing a problem in the last line of my code, where the attribute pixel_values is not recognized and I am getting an

error: raise AttributeError.

The same issue I got when I run the code through the google colab.

I am firstly, trying to understand what this pixel_values does in general and how to solve this issue.

[NielsRogge]

Hi, yes it should be input_ids instead of pixel_values. Will fix, thanks for reporting!

[NielsRogge]

It's fixed now! https://github.com/NielsRogge/Transformers-Tutorials/blob/master/ImageGPT/Linear_probing_with_ImageGPT.ipynb