Read me fisrt

yihuacheng · Dec 18, 2019 · b238d8d · b238d8d
1 parent 5636596
commit b238d8d
Showing 1 changed file with 21 additions and 26 deletions.
diff --git a/README.md b/README.md
@@ -2,13 +2,13 @@
 
 
 ## Introduction
-This is the README file for the official code associated with the ECCV2018 paper, "Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric Regression". 
+This is the README file for the official code associated with the ECCV2018 paper, "Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric Regression".<br>
 
-Our academic paper which describe ARE-Net in detail and provides full result can be found here: \[[PAPER]( http://openaccess.thecvf.com/content_ECCV_2018/papers/Yihua_Cheng_Appearance-Based_Gaze_Estimation_ECCV_2018_paper.pdf)\].
+Our academic paper which describe ARE-Net in detail and provides full result can be found here: \[[PAPER]( http://openaccess.thecvf.com/content_ECCV_2018/papers/Yihua_Cheng_Appearance-Based_Gaze_Estimation_ECCV_2018_paper.pdf)\].<br>
 
 
 ## Usage
-We also ask that you cite the associated paper if you make use of this dataset; following is the BibTeX entry:
+We also ask that you cite the associated paper if you make use of this dataset; following is the BibTeX entry:<br>
 ```
 @inproceedings{eccv2018_are,
 Author = {Yihua Cheng and Feng Lu and Xucong Zhang},
@@ -19,7 +19,7 @@ Booktitle = {European Conference on Computer Vision (ECCV)}
 ```
 
 ## Enviroment
-To using this code, you should make sure following libraries are installed first.
+To using this code, you should make sure following libraries are installed first.<br>
 ```
 Python>=3
 Tensorflow-GPU>=1.10
@@ -28,37 +28,32 @@ numpy, os, math etc., which can be found in the head of code.
 ``` 
 
 ## Code
-You need to modify the **config.yaml** first especially *data/label* and *data/root* params.  
-*data/label* represents the path of label file.  
-*data/root* represents the path of image file.  
+You need to modify the **config.yaml** first especially *data/label* and *data/root* params.<br>  
+*data/label* represents the path of label file.<br>  
+*data/root* represents the path of image file.<br>  
 
-A example of label file is **data** folder. Each line in label file is conducted as:
+A example of label file is **data** folder. Each line in label file is conducted as:<br>
 ```
 p00/left/1.bmp p00/right/1.bmp p00/day08/0069.bmp -0.244513310176,0.0520949295694,-0.968245505778 ... ...
 ```
-Where our code reads image data form `os.path.join(data/root, "p00/left/1.bmp")` and reads gts of gaze direction from the rest in label file.
+Where our code reads image data form `os.path.join(data/root, "p00/left/1.bmp")` and reads gts of gaze direction from the rest in label file.<br>
 
-**Train**: We use mode 1 to represent train mode. You can train model with:
-```
-python main.py -m 1
-```
+## Run the code
+We provide two optional args, which are -m and -n.<br>  
+-m represet the running mode. We use 1 for train mode, 2 for predict mode and 3 for evaluate mode.<br>
 
-**Predict**: We use mode 2 to predict result. You can predcit result with
-```
-python main.py -m 2 
-```
-Note that, you can not get accuracy in this mode.
+You can train model with 1, get predicted result with 2 and get model accuracy with 3.<br>
 
-**Evaluate**: We use mode 3 to evaluate trained model. You can use this mode to obtain accuracy of our model.
+For example, you can use the code like:<br>
 ```
-python main.py -m 3
+python main.py -m 13
 ```
+to train and evaluate model together.<br>
 
-Meanwhile, you can also use the code like:
+-n represet the number of test file in 'leave-one-person-out' strategy.<br>
+For example, *data/label* provide 15 label file. Use
 ```
-python main.py -m 13
+python main.py -m 13 -n 0
 ```
-to train and evaluate model together.
-
-
-
+you train and evaluate the model with using the first person (p00.label) as test file. <br>
+Note that, we add a loop in **main.py** to perform `leave-one-person-out` automatically. You can delete it for your individual usage.<br>