This repository is to do Human Parsing with SegNet.
Follow the instruction to download Look-Into-Person dataset.
Download VGG16 into models folder.
Extract training images:
$ python pre_process.py$ python train.pyIf you want to visualize during training, run in your terminal:
$ tensorboard --logdir path_to_current_dir/logsDownload pre-trained model and put it into models folder.
$ python demo.py| Input | Merged | Output |
|---|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |