Update README.md
Browse files
README.md
CHANGED
|
@@ -78,16 +78,6 @@ score, joint_embedding = model.encode_multimodal(
|
|
| 78 |
|
| 79 |
There are two options to calculate semantic compatibility between an image and a text: cosine similarity and [Matching Score](#matching-score).
|
| 80 |
|
| 81 |
-
### Cosine Similarity
|
| 82 |
-
|
| 83 |
-
```python
|
| 84 |
-
import torch.nn.functional as F
|
| 85 |
-
|
| 86 |
-
similarity = F.cosine_similarity(image_embedding, text_embedding)
|
| 87 |
-
```
|
| 88 |
-
|
| 89 |
-
The `similarity` will belong to the `[-1, 1]` range, `1` meaning the absolute match.
|
| 90 |
-
|
| 91 |
__Pros__:
|
| 92 |
|
| 93 |
- Computationally cheap.
|
|
|
|
| 78 |
|
| 79 |
There are two options to calculate semantic compatibility between an image and a text: cosine similarity and [Matching Score](#matching-score).
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
__Pros__:
|
| 82 |
|
| 83 |
- Computationally cheap.
|