File size: 798 Bytes
c81f977 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | # Prosody ViT Image Classifier
Fine-tuned `google/vit-base-patch16-224` for binary page classification in the
[Princeton Prosody Archive](https://prosody.princeton.edu/) corpus, using the
scanned page **image** only.
- **Classes:** `TU` (0), `non-TU` (1)
- **Architecture:** `ViTForImageClassification` (HF-native)
```python
from transformers import AutoModelForImageClassification, AutoImageProcessor
from PIL import Image
import torch
model = AutoModelForImageClassification.from_pretrained("./vit-image")
proc = AutoImageProcessor.from_pretrained("./vit-image")
img = Image.open("page.png").convert("RGB")
inp = proc(img, return_tensors="pt")
with torch.no_grad():
probs = model(**inp).logits.softmax(-1)[0]
print({model.config.id2label[i]: float(p) for i, p in enumerate(probs)})
```
|