Feature Extraction
Transformers
clip
vision
Inference Endpoints
kimihailv commited on
Commit
c47f742
1 Parent(s): 8d948b2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -20,6 +20,15 @@ This is model card of the __English only model__ with:
20
 
21
  If you need Multilingual model, check [this](https://huggingface.co/unum-cloud/uform-vl-multilingual).
22
 
 
 
 
 
 
 
 
 
 
23
  ## Installation
24
 
25
  ```bash
 
20
 
21
  If you need Multilingual model, check [this](https://huggingface.co/unum-cloud/uform-vl-multilingual).
22
 
23
+ ## Evaluation
24
+
25
+ The following metrics were obtained with multimodal re-ranking:
26
+
27
+ | Dataset | Recall@1 | Recall@5 | Recall@10 |
28
+ | :-------- | ------: | --------: | --------: |
29
+ | Zero-Shot Flickr | 0.727 | 0.915 | 0.949 |
30
+ | MS-COCO (train split was in training data) | 0.510 | 0.761 | 0.838 |
31
+
32
  ## Installation
33
 
34
  ```bash