Hugging Face's logo

ClementP
/
FundusDRGrading-vit_small_patch14_dinov2

Transformers
PyTorch
Safetensors
English
fundus
diabetic retinopathy
classification
Eval Results
Inference Endpoints
Model card Files Community
ClementP commited on
Commit
7d14a9d
•
1 Parent(s): e73bb45

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +51 -5
README.md CHANGED
@@ -1,9 +1,55 @@
1
  ---
 
 
2
  tags:
3
- - pytorch_model_hub_mixin
4
- - model_hub_mixin
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  ---
 
 
 
 
 
 
 
 
 
 
6
 
7
- This model has been pushed to the Hub using ****:
8
- - Repo: [More Information Needed]
9
- - Docs: [More Information Needed]
 
1
  ---
2
+ language: en
3
+ license: mit
4
  tags:
5
+ - fundus
6
+ - diabetic retinopathy
7
+ - classification
8
+ datasets:
9
+ - APTOS
10
+ - EYEPACS
11
+ - IDRID
12
+ - DDR
13
+ library: timm
14
+ model-index:
15
+ - name: vit_small_patch14_dinov2
16
+ results:
17
+ - task:
18
+ type: image-classification
19
+ dataset:
20
+ name: EYEPACS
21
+ type: EYEPACS
22
+ metrics:
23
+ - type: kappa
24
+ value: 0.7281550168991089
25
+ name: Quadratic Kappa
26
+ - task:
27
+ type: image-classification
28
+ dataset:
29
+ name: IDRID
30
+ type: IDRID
31
+ metrics:
32
+ - type: kappa
33
+ value: 0.7765608429908752
34
+ name: Quadratic Kappa
35
+ - task:
36
+ type: image-classification
37
+ dataset:
38
+ name: DDR
39
+ type: DDR
40
+ metrics:
41
+ - type: kappa
42
+ value: 0.7057451009750366
43
+ name: Quadratic Kappa
44
  ---
45
+ # Fundus DR Grading
46
+
47
+ [![Rye](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/rye/main/artwork/badge.json)](https://rye-up.com)
48
+ [![PyTorch](https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white)](https://pytorch.org/docs/stable/index.html)
49
+ [![Lightning](https://img.shields.io/badge/Lightning-792ee5?logo=lightning&logoColor=white)](https://lightning.ai/docs/pytorch/stable/)
50
+
51
+ ## Description
52
+
53
+ This project aims to evaluate the performance of different models for the classification of diabetic retinopathy (DR) in fundus images. The reported perfomance metrics are not always consistent in the literature. Our goal is to provide a fair comparison between different models using the same datasets and evaluation protocol.
54
+
55