4rtemi5 commited on
Commit
4f04fa9
1 Parent(s): 4a0f49b

Update readme.md

Browse files
Files changed (1) hide show
  1. readme.md +5 -5
readme.md CHANGED
@@ -5,7 +5,7 @@ With a few tricks, we have been able to fine-tune a competitive Italian CLIP mod
5
  In building this project we kept in mind the following things:
6
 
7
  + **Novel Contributions**: We created a dataset of ~1.4 million Italian image-text pairs and to our knowledge trained the best Italian CLIP model currently in existence;
8
- + **Scientific Validity**: Claim are easy, facts are hard. That's why validation is important to assess the real impact of a model. That's why we thoroughly evaluated our models and made the validation reproducible for everybody.
9
  + **Broader Outlook**: we always considered which are the possible usages for this model.
10
 
11
  We put our **hearts** and **souls** into the project during this week! Not only did we work on a cool project, but we were
@@ -80,10 +80,10 @@ We selected two different tasks:
80
 
81
  | Accuracy | CLIP-Italian | mCLIP |
82
  | --------------- | ------------ |-------|
83
- | Accuracy@1 | | |
84
- | Accuracy@5 | | |
85
- | Accuracy@10 | | |
86
- | Accuracy@100 | 81.08 | 67.11 |
87
 
88
  ## Qualitative Evaluation
89
 
 
5
  In building this project we kept in mind the following things:
6
 
7
  + **Novel Contributions**: We created a dataset of ~1.4 million Italian image-text pairs and to our knowledge trained the best Italian CLIP model currently in existence;
8
+ + **Scientific Validity**: Claim are easy, facts are hard. That's why validation is important to assess the real impact of a model. We thoroughly evaluated our models and made the validation reproducible for everybody.
9
  + **Broader Outlook**: we always considered which are the possible usages for this model.
10
 
11
  We put our **hearts** and **souls** into the project during this week! Not only did we work on a cool project, but we were
 
80
 
81
  | Accuracy | CLIP-Italian | mCLIP |
82
  | --------------- | ------------ |-------|
83
+ | Accuracy@1 | **22.11** | 20.15 |
84
+ | Accuracy@5 | **43.69** | 36.57 |
85
+ | Accuracy@10 | **52.55** | 42.91 |
86
+ | Accuracy@100 | **81.08** | 67.11 |
87
 
88
  ## Qualitative Evaluation
89