Inoob commited on
Commit
15f087a
·
verified ·
1 Parent(s): 4d15c0a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -4
README.md CHANGED
@@ -2,10 +2,21 @@
2
  license: apache-2.0
3
  ---
4
  # Handwriting-Removal-DIS
 
5
 
6
- *NOTE: THIS IS A CLONE README FROM THE [ORIGINAL GITHUB REPO](https://github.com/ivanhe123/Handwriting-Removal-DIS/)*
7
 
8
- My effort into improving handwriting removal throught the new DIS (Dichotomous Image Segmentation)
 
 
 
 
 
 
 
 
 
 
9
 
10
  ## Related Research
11
  AndSonder has also done research and experimentaion on the same subject but using deeplabv3+ to segment the handwriting.
@@ -56,5 +67,3 @@ The code that was used to generate the dataset in the Huggingface Repo is ```cre
56
  ## Training
57
 
58
  I used the ```train_valid_inference_main.py``` from [DIS](https://github.com/xuebinqin/DIS) with my own dataset and training batch size.
59
-
60
- You can scale the batch size up if you have enough memory.
 
2
  license: apache-2.0
3
  ---
4
  # Handwriting-Removal-DIS
5
+ My effort into improving handwriting removal throught the new [DIS (Dichotomous Image Segmentation)](https://github.com/xuebinqin/DIS)
6
 
7
+ ## Inference
8
 
9
+ 1. Clone the DIS github:
10
+
11
+ ```cmd
12
+ git clone https://github.com/xuebinqin/DIS
13
+ ```
14
+
15
+ 2. Install the requirements via ```pip install -r requirements.txt```
16
+
17
+ 3. Replace ```Inference.py``` in the cloned DIS folder to the ```Inference.py``` of this repository.
18
+
19
+ 4. Change the paths according to your own application.
20
 
21
  ## Related Research
22
  AndSonder has also done research and experimentaion on the same subject but using deeplabv3+ to segment the handwriting.
 
67
  ## Training
68
 
69
  I used the ```train_valid_inference_main.py``` from [DIS](https://github.com/xuebinqin/DIS) with my own dataset and training batch size.