Ozan Oktay
commited on
Commit
•
b893a24
1
Parent(s):
06ca26f
Update README.md
Browse files
README.md
CHANGED
|
@@ -59,6 +59,10 @@ The primary intended use is to support AI researchers building on top of this wo
|
|
| 59 |
Here is how to use this model to extract radiological sentence embeddings and obtain their cosine similarity in the joint space (image and text):
|
| 60 |
|
| 61 |
```python
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
# Load the model and tokenizer
|
| 63 |
url = "microsoft/BiomedVLP-CXR-BERT-specialized"
|
| 64 |
tokenizer = AutoTokenizer.from_pretrained(url, trust_remote_code=True)
|
|
|
|
| 59 |
Here is how to use this model to extract radiological sentence embeddings and obtain their cosine similarity in the joint space (image and text):
|
| 60 |
|
| 61 |
```python
|
| 62 |
+
import torch
|
| 63 |
+
|
| 64 |
+
from transformers import AutoModel, AutoTokenizer
|
| 65 |
+
|
| 66 |
# Load the model and tokenizer
|
| 67 |
url = "microsoft/BiomedVLP-CXR-BERT-specialized"
|
| 68 |
tokenizer = AutoTokenizer.from_pretrained(url, trust_remote_code=True)
|