MalumaDev commited on
Commit
8e6767d
·
verified ·
1 Parent(s): 6b03e26

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -4,14 +4,14 @@
4
  This project aims at bridging the gap between medical image analysis by introducing a light colorization module. Three different modules are proposed and implemented (DECONV, PixelShuffle and ColorU)
5
 
6
 
7
- ![Modules](/images/MODULES.png)
8
 
9
  The modules are trained jointly with a backbone pre-trained on ImageNet. A multi-stage transfer learning pipeline is summarized here.
10
  First, the colorization module is trained from scratch together with the classifier, while the pre-trained CNN backbone is kept frozen, to learn the mapping which maximizes classification accuracy.
11
  Then, the entire network is fine-tuned to learn useful features for the target task, while simultaneously adjusting the colorization mapping. The figure below shows the output of each colorization module when only the colorization module is trained, and after the entire network is fine-tuned.
12
 
13
 
14
- ![Colorization](/images/paper_images.jpg)
15
 
16
  ## Dependencies
17
 
 
4
  This project aims at bridging the gap between medical image analysis by introducing a light colorization module. Three different modules are proposed and implemented (DECONV, PixelShuffle and ColorU)
5
 
6
 
7
+ ![Modules](./images/MODULES.png)
8
 
9
  The modules are trained jointly with a backbone pre-trained on ImageNet. A multi-stage transfer learning pipeline is summarized here.
10
  First, the colorization module is trained from scratch together with the classifier, while the pre-trained CNN backbone is kept frozen, to learn the mapping which maximizes classification accuracy.
11
  Then, the entire network is fine-tuned to learn useful features for the target task, while simultaneously adjusting the colorization mapping. The figure below shows the output of each colorization module when only the colorization module is trained, and after the entire network is fine-tuned.
12
 
13
 
14
+ ![Colorization](images/paper_images.jpg)
15
 
16
  ## Dependencies
17