Implementing the paper: Fully Convolutional Networks for Semantic Segmentation
This code simplely implement the paper Fully Convolutional Networks for Semantic Segmentation
Dataset is a little small, we just use PASCAL VOC 2007, which includes about 400 segmentation iamges.
Dataset PASCAL VOC 2007: https://pjreddie.com/media/files/VOCtrainval_06-Nov-2007.tar
pretrained vgg16: https://drive.google.com/open?id=1LTptCY96ABAUlJHUJq6MhqNrDQN7JfQP
- putting vgg16.npy into the folder 'vgg_para'
- unzipping VOCtrainval_06-Nov-2007.tar and
- python 3.5
- tensorflow-gpu 1.4.0
- pillow
- scipy
- numpy
- matplotlib
Movie | IMG1 | IMG2 |
---|---|---|
I Am Legend | ||
Resident Evil | ||
The Walking Dead |