Feature Extraction
clip
vision
kimihailv commited on
Commit
2efb554
·
verified ·
1 Parent(s): c0946ae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -129,7 +129,7 @@ To load the model:
129
  ```python
130
  import uform
131
 
132
- model = uform.get_model('unum-cloud/uform-vl-multilingual-v2')
133
  ```
134
 
135
  To encode data:
@@ -140,11 +140,11 @@ from PIL import Image
140
  text = 'a small red panda in a zoo'
141
  image = Image.open('red_panda.jpg')
142
 
143
- image_data = model.preprocess_image(image)
144
- text_data = model.preprocess_text(text)
145
 
146
- image_embedding = model.encode_image(image_data)
147
- text_embedding = model.encode_text(text_data)
148
  joint_embedding = model.encode_multimodal(image=image_data, text=text_data)
149
  ```
150
 
 
129
  ```python
130
  import uform
131
 
132
+ model, processor = uform.get_model('unum-cloud/uform-vl-multilingual-v2')
133
  ```
134
 
135
  To encode data:
 
140
  text = 'a small red panda in a zoo'
141
  image = Image.open('red_panda.jpg')
142
 
143
+ image_data = processor.preprocess_image(image)
144
+ text_data = processor.preprocess_text(text)
145
 
146
+ image_features, image_embedding = model.encode_image(image_data, return_features=True)
147
+ text_features, text_embedding = model.encode_text(text_data, return_features=True)
148
  joint_embedding = model.encode_multimodal(image=image_data, text=text_data)
149
  ```
150