From 8130017f415afc3c99e0f68b871649167d588bea Mon Sep 17 00:00:00 2001
From: rmaphoh <rmaphoh@ucl.ac.uk>
Date: Sat, 27 Jan 2024 12:51:14 +0000
Subject: [PATCH] data and checkpoints

---
 README.md | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 7739282..5005454 100644
--- a/README.md
+++ b/README.md
@@ -63,10 +63,21 @@ To fine tune RETFound on your own data, follow these steps:
 
 2. Organise your data into this directory structure (Public datasets used in this study can be [downloaded here](BENCHMARK.md))
 
-<p align="left">
-  <img src="./pic/file_index.jpg" width="160">
-</p>
-
+```
+├── data folder
+    ├──train
+        ├──class_a
+        ├──class_b
+        ├──class_c
+    ├──val
+        ├──class_a
+        ├──class_b
+        ├──class_c
+    ├──test
+        ├──class_a
+        ├──class_b
+        ├──class_c
+``` 
 
 3. Start fine-tuning (use IDRiD as example). A fine-tuned checkpoint will be saved during training. Evaluation will be run after training.