[Python] Can't load the model for 'openai/clip-vit-base-patch32'

Environments


Windows 11 x86_64

Python 3.12.6

Cuda 12.6

Details


I follow huggingface offical guide guide to run the code

from PIL import Image
import requests

from transformers import CLIPProcessor, CLIPModel

model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")

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

inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)

outputs = model(**inputs)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities


However, when I type 'python main.py'. It always shows

OSError: Can't load the model for 'openai/clip-vit-base-patch32'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'openai/clip-vit-base-patch32' is the correct path to a directory containing a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.
​

Solutions I tried


I tried different version of python and environment(venv and normal).

I tried delete the hugging face cache at ~/.cache/huggingface.

I believed that my network can access huggingface.

I tried the code in my WSL2, it goes well, but when I do the same step in Windows, it goes bad.

Thanks a lot!

Continue reading...