https://github.com/mingtaoguo/fcn_segmentation_tensorflow
Implementing the paper: Fully Convolutional Networks for Semantic Segmentation
https://github.com/mingtaoguo/fcn_segmentation_tensorflow
fcn image-segmentation tensorflow
Last synced: 7 months ago
JSON representation
Implementing the paper: Fully Convolutional Networks for Semantic Segmentation
- Host: GitHub
- URL: https://github.com/mingtaoguo/fcn_segmentation_tensorflow
- Owner: MingtaoGuo
- Created: 2019-07-12T07:39:23.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2019-07-12T12:02:04.000Z (about 6 years ago)
- Last Synced: 2025-01-21T16:44:47.826Z (9 months ago)
- Topics: fcn, image-segmentation, tensorflow
- Language: Python
- Size: 224 KB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# FCN_segmentation
Implementing the paper: Fully Convolutional Networks for Semantic Segmentation# Introduction
This code simplely implement the paper [Fully Convolutional Networks for Semantic Segmentation](https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf)

# Dataset
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
1. putting vgg16.npy into the folder 'vgg_para'
2. unzipping VOCtrainval_06-Nov-2007.tar and
# Requirements
1. python 3.5
2. tensorflow-gpu 1.4.0
3. pillow
4. scipy
5. numpy
6. matplotlib
# Results
|Movie|IMG1|IMG2|
|-|-|-|
|I Am Legend|||
|Resident Evil|||
|The Walking Dead|||