AI Rank
EN
← 开源
foamliu

Deep-Image-Matting

Deep Image Matting

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
991
Star
259
Fork
+0
本周
4
贡献者
创建于 2018-04-16 · 更新于 2026-09-30 · 今日第 12195 名
主要开发者
foamliufoamliu-msFantasyJXF

foamliu/Deep-Image-Matting 排名第 12,195，有 991 个星标。

同类别比较

foamliu/Deep-Image-Matting 排名第 12,195，此处有 8 个同类条目；google-research/augmix 排名第 12,196。

同类别比较
名称排名指标
molecularsets/moses12,180
语言:
Python
星标数:
993
分叉数:
282
简介:
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
mxgmn/TextureSynthesis12,186
语言:
C#
星标数:
992
分叉数:
55
简介:
Texture synthesis from examples
MaurizioFD/RecSys2019_DeepLearning_Evaluation12,189
语言:
Python
星标数:
991
分叉数:
251
简介:
This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.
dgasmith/opt_einsum12,192
语言:
Python
星标数:
991
分叉数:
78
简介:
⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.
google-research/augmix12,196
语言:
Python
星标数:
991
分叉数:
156
简介:
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
KaiyangZhou/pytorch-center-loss12,200
语言:
Python
星标数:
990
分叉数:
216
简介:
Pytorch implementation of Center Loss
clcarwin/focal_loss_pytorch12,203
语言:
Python
星标数:
990
分叉数:
216
简介:
A PyTorch Implementation of Focal Loss.
tensorflow/transform12,206
语言:
Python
星标数:
990
分叉数:
225
简介:
Input pipeline framework
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
关键词Image production
星标数991
分叉数259
贡献者4
创建日期2018-04-16
更新日期2026-09-30
1 天星标数0
7 天星标数0
排名12,195
上次排名12,122
排名变化-73
7 天星标排名13,311
上次 7 天星标排名13,322
7 天星标排名变化11
总星标排名11,229
上次总星标排名11,208
总星标排名变化-21
国家China
README 摘录

Just in case you are interested, Deep Image Matting v2 is an upgraded version of this. Deep Image Matting This repository is to reproduce Deep Image Matting. 6 OpenCV Dataset Adobe Deep Image Matting Dataset Follow the instruction to contact author for the dataset. MSCOCO Go to MSCOCO to download: 2014 Train images PASCAL VOC Go to PASCAL VOC to download: VOC challenge 2008 training/validation data The test data for the VOC2008 challenge ImageNet Pretrained Models Download VGG16 into

"models" folder.

常见问题

记录了多少星标和分叉？

foamliu/Deep-Image-Matting 有 991 个星标和 259 个分叉。

仓库排名是多少？

foamliu/Deep-Image-Matting 排名第 12,195。

记录的语言和类别是什么？

foamliu/Deep-Image-Matting 有 991 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

foamliu/Deep-Image-Matting 与 google-research/augmix 比较，后者排名第 12,196，有 991 个星标。

README

Just in case you are interested, Deep Image Matting v2 is an upgraded version of this.

Deep Image Matting

This repository is to reproduce Deep Image Matting.

Dependencies

Dataset

Adobe Deep Image Matting Dataset

Follow the instruction to contact author for the dataset.

MSCOCO

Go to MSCOCO to download:

PASCAL VOC

Go to PASCAL VOC to download:

ImageNet Pretrained Models

Download VGG16 into "models" folder.

Usage

Data Pre-processing

Extract training images:

$ python pre_process.py

Train

$ python train.py

If you want to visualize during training, run in your terminal:

$ tensorboard --logdir path_to_current_dir/logs

Demo

Download pre-trained Deep Image Matting Model to "models" folder then run:

$ python demo.py
Image/Trimap Output/GT New BG/Compose
排名相邻
同类项目