GoodBaiBai88
commited on
Commit
•
51f3fd7
1
Parent(s):
10543c8
Update README.md
Browse files
README.md
CHANGED
@@ -12,8 +12,8 @@ M3D-CLIP is a 3D medical CLIP model, which aligns vision and language through co
|
|
12 |
The vision encoder uses 3D ViT with 32*256*256 image size and 4*16*16 patch size.
|
13 |
The text encoder utilizes a pre-trained BERT as initialization.
|
14 |
|
15 |
-
![
|
16 |
-
![
|
17 |
|
18 |
# Quickstart
|
19 |
|
|
|
12 |
The vision encoder uses 3D ViT with 32*256*256 image size and 4*16*16 patch size.
|
13 |
The text encoder utilizes a pre-trained BERT as initialization.
|
14 |
|
15 |
+
![comparison](M3D_CLIP_table.png)
|
16 |
+
![comparison](itr_result.png)
|
17 |
|
18 |
# Quickstart
|
19 |
|