jdelgado2002
commited on
Commit
•
4342dc1
1
Parent(s):
f5d08d2
Update README.md
Browse files
README.md
CHANGED
@@ -31,10 +31,24 @@ Greetings fellow fastlearner 🤝! Don't forget to delete this content from your
|
|
31 |
# Model card
|
32 |
|
33 |
## Model description
|
34 |
-
|
35 |
|
36 |
## Intended uses & limitations
|
37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
|
39 |
## Training and evaluation data
|
40 |
-
|
|
|
|
|
|
31 |
# Model card
|
32 |
|
33 |
## Model description
|
34 |
+
This is an image categorization model that uses restnet-50 as the base model to classify diabetic retinopathy
|
35 |
|
36 |
## Intended uses & limitations
|
37 |
+
Given an image taken using fundus photography
|
38 |
+
this model will identify diabetic retinopathy on a scale of 0 to 4:
|
39 |
+
|
40 |
+
0 - No DR
|
41 |
+
|
42 |
+
1 - Mild
|
43 |
+
|
44 |
+
2 - Moderate
|
45 |
+
|
46 |
+
3 - Severe
|
47 |
+
|
48 |
+
4 - Proliferative DR
|
49 |
+
|
50 |
|
51 |
## Training and evaluation data
|
52 |
+
* We trained our model with retina images taken using fundus photography under a variety of imaging conditions.
|
53 |
+
* The training data was gathered for a Kaggle completion by the Asia Pacific Tele-Ophthalmology Society (APTOS) in 2019
|
54 |
+
* [Training data](https://www.kaggle.com/competitions/aptos2019-blindness-detection/data)
|