@@ -9,9 +9,12 @@ Automatic age and gender classification based on unconstrained images has become
9
9
## Citing Paper
10
10
If you find our works useful in your research, please consider citing:
11
11
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
+ }
15
18
16
19
## Prerequisition
17
20
- Python 2.7
@@ -28,6 +31,16 @@ $ git clone --recursive https://github.com/ivclab/agegenderLMTCNN.git
28
31
``` bash
29
32
$ python download_adiencedb.py
30
33
```
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
+
31
44
32
45
## Coming Soon ...
33
46
0 commit comments