All Projects → dongwu92 → Autoportraitmatting

dongwu92 / Autoportraitmatting

Licence: apache-2.0
Tensorflow implementation of Automatic Portrait Matting on paper "Automatic Portrait Segmentation for Image Stylization"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Autoportraitmatting

Fcn train
The code includes all the file that you need in the training stage for FCN
Stars: ✭ 104 (-78.11%)
Mutual labels:  fcn
instance-segmentation
No description or website provided.
Stars: ✭ 40 (-91.58%)
Mutual labels:  fcn
DL Notes
DL & CV & Neural Network
Stars: ✭ 29 (-93.89%)
Mutual labels:  fcn
Hyperdensenet
This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-73.89%)
Mutual labels:  fcn
Fcn For Semantic Segmentation
Implemention of FCN-8 and FCN-16 with Keras and uses CRF as post processing
Stars: ✭ 155 (-67.37%)
Mutual labels:  fcn
tempo-cnn
Framework for estimating temporal properties of music tracks.
Stars: ✭ 62 (-86.95%)
Mutual labels:  fcn
Pytorch Fcn
PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
Stars: ✭ 1,351 (+184.42%)
Mutual labels:  fcn
Image Segmentation
Implementation of FCN (8/16/32) in Tensorflow. 🌀 在TensorFlow框架下实现 FCN (全卷积神经网络) 。
Stars: ✭ 19 (-96%)
Mutual labels:  fcn
Fcn
Chainer Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
Stars: ✭ 211 (-55.58%)
Mutual labels:  fcn
FCN-Segmentation-TensorFlow
FCN for Semantic Image Segmentation achieving 68.5 mIoU on PASCAL VOC
Stars: ✭ 34 (-92.84%)
Mutual labels:  fcn
Pytorch Fcn Easiest Demo
PyTorch Implementation of Fully Convolutional Networks (a very simple and easy demo).
Stars: ✭ 138 (-70.95%)
Mutual labels:  fcn
Keras Segmentation
Get started with Semantic Segmentation based on Keras, including FCN32/FCN8/SegNet/U-Net
Stars: ✭ 151 (-68.21%)
Mutual labels:  fcn
Fashion-Clothing-Parsing
FCN, U-Net models implementation in TensorFlow for fashion clothing parsing
Stars: ✭ 29 (-93.89%)
Mutual labels:  fcn
Unet Segmentation In Keras Tensorflow
UNet is a fully convolutional network(FCN) that does image segmentation. Its goal is to predict each pixel's class. It is built upon the FCN and modified in a way that it yields better segmentation in medical imaging.
Stars: ✭ 105 (-77.89%)
Mutual labels:  fcn
DDUnet-Modified-Unet-for-WMH-with-Dense-Dilate
WMH segmentaion with unet, dilated_unet, and with ideas from denseNet
Stars: ✭ 23 (-95.16%)
Mutual labels:  fcn
Segmentation
Tensorflow implementation : U-net and FCN with global convolution
Stars: ✭ 101 (-78.74%)
Mutual labels:  fcn
tf-semantic-segmentation-FCN-VGG16
Semantic segmentation for classifying road. "Fully Convolutional Networks for Semantic Segmentation (2015)" implemented using TF
Stars: ✭ 30 (-93.68%)
Mutual labels:  fcn
Piwise
Pixel-wise segmentation on VOC2012 dataset using pytorch.
Stars: ✭ 365 (-23.16%)
Mutual labels:  fcn
TensorFlow-Advanced-Segmentation-Models
A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.
Stars: ✭ 64 (-86.53%)
Mutual labels:  fcn
Brain-Tumor-Segmentation-using-Topological-Loss
A Tensorflow Implementation of Brain Tumor Segmentation using Topological Loss
Stars: ✭ 28 (-94.11%)
Mutual labels:  fcn

AutoPortraitMatting

Tensorflow implementation of Automatic Portrait Matting on paper "Automatic Portrait Segmentation for Image Stylization"

Requirement

  • Tensorflow
  • scipy
  • six
  • PIL
  • numpy

Data

mkdir Model_zoo and download http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat

download data from http://xiaoyongshen.me/webpage_portrait/index.html

mkdir data and copy the following folders and files into data/:

  • images_mask/
  • images_data/
  • images_data_crop/
  • images_tracker/
  • portraitFCN_data/
  • portraitFCN+_data/
  • meanmask.png
  • testlist.mat
  • trainlist.mat

Some of the folders data above, will be obtained by additional scripting. To obtain additional data, run the data_download.m and generate_data_file.m respectively

How to run

FCN.py and FCN_puls.py implements the two models in that paper. To train:

if __name__ == "__main__": tf.app.run() #pred()

After train, predict:

if __name__ == "__main__": #tf.app.run() pred()

Datasets

由于shenxiaoyong网站崩溃,提供数据的百度云下载链接 Link: http://pan.baidu.com/s/1dE14537 Password: ndg8 仅供学术交流,如有引用,请通知原作者。

Ackownledge

Thanks for Xiaoyong Shen and his paper

"Deep Automatic Portrait Matting" Xiaoyong Shen, Xin Tao, Hongyun Gao, Chao Zhou, Jiaya Jia. European Conference on Computer Vision (ECCV), 2016

I can't reach the performance in this paper. So please modify it as you want and inform me if any improvement.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].