Skip to content

Commit bc1dfce

Browse files
add data preparation
1 parent c489283 commit bc1dfce

File tree

1 file changed

+16
-3
lines changed

1 file changed

+16
-3
lines changed

README.md

+16-3
Original file line numberDiff line numberDiff line change
@@ -9,9 +9,12 @@ Automatic age and gender classification based on unconstrained images has become
99
## Citing Paper
1010
If you find our works useful in your research, please consider citing:
1111

12-
Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications
13-
J.-H. Lee, Y.-M. Chan, T.-Y. Chen, C.-S Chen
14-
IEEE International Conference on Multimedia Information Processing and Retrieval, MIPR 2018
12+
@inproceedings{
13+
Title = {Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications},
14+
Author = {Lee, Jia-Hong and Chan, Yi-Ming and Chen, Ting-Yen and Chen, Chu-Song},
15+
booktitle = {IEEE International Conference on Multimedia Information Processing and Retrieval, MIPR},
16+
year = {2018}
17+
}
1518

1619
## Prerequisition
1720
- Python 2.7
@@ -28,6 +31,16 @@ $ git clone --recursive https://github.com/ivclab/agegenderLMTCNN.git
2831
```bash
2932
$ python download_adiencedb.py
3033
```
34+
3. Split raw data into training set, validation set and testing set per fold for five-fold validation.
35+
this project have been generated this files in DataPreparation/FiveFolds/train_val_test_per_fold_agegender.
36+
if you want to generate the new one, you can utilize the following command:
37+
```bash
38+
$ python datapreparation.py \
39+
--inputdir=./adiencedb/aligned \
40+
--rawfoldsdir=./DataPreparation/FiveFolds/original_txt_files \
41+
--outfilesdir=./DataPreparation/FiveFolds/train_val_test_per_fold_agegender
42+
```
43+
3144

3245
## Coming Soon ...
3346

0 commit comments

Comments
 (0)