Update README.md
Browse files
README.md
CHANGED
@@ -65,38 +65,6 @@ These weights are directly usable in OpenCLIP (image + text).
|
|
65 |
| GeoDE | 0.9253 |
|
66 |
| **Average** | **0.68039** |
|
67 |
|
68 |
-
## Model Usage
|
69 |
-
### With OpenCLIP
|
70 |
-
```
|
71 |
-
import torch
|
72 |
-
import torch.nn.functional as F
|
73 |
-
from urllib.request import urlopen
|
74 |
-
from PIL import Image
|
75 |
-
from open_clip import create_model_from_pretrained, get_tokenizer
|
76 |
-
|
77 |
-
model, preprocess = create_model_from_pretrained('hf-hub:apple/DFN2B-CLIP-ViT-L-14')
|
78 |
-
tokenizer = get_tokenizer('ViT-L-14')
|
79 |
-
|
80 |
-
image = Image.open(urlopen(
|
81 |
-
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
|
82 |
-
))
|
83 |
-
image = preprocess(image).unsqueeze(0)
|
84 |
-
|
85 |
-
labels_list = ["a dog", "a cat", "a donut", "a beignet"]
|
86 |
-
text = tokenizer(labels_list, context_length=model.context_length)
|
87 |
-
|
88 |
-
with torch.no_grad(), torch.cuda.amp.autocast():
|
89 |
-
image_features = model.encode_image(image)
|
90 |
-
text_features = model.encode_text(text)
|
91 |
-
image_features = F.normalize(image_features, dim=-1)
|
92 |
-
text_features = F.normalize(text_features, dim=-1)
|
93 |
-
|
94 |
-
text_probs = torch.sigmoid(image_features @ text_features.T * model.logit_scale.exp() + model.logit_bias)
|
95 |
-
|
96 |
-
zipped_list = list(zip(labels_list, [round(p.item(), 3) for p in text_probs[0]]))
|
97 |
-
print("Label probabilities: ", zipped_list)
|
98 |
-
```
|
99 |
-
|
100 |
## Citation
|
101 |
```bibtex
|
102 |
@article{fang2023data,
|
|
|
65 |
| GeoDE | 0.9253 |
|
66 |
| **Average** | **0.68039** |
|
67 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
## Citation
|
69 |
```bibtex
|
70 |
@article{fang2023data,
|