AI Rank
EN
← 开源
zllrunning

face-parsing.PyTorch

Using modified BiSeNet for face parsing in PyTorch

ModelsVision modelsPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
2.59k
Star
497
Fork
+1
本周
1
贡献者
创建于 2019-04-18 · 更新于 2026-10-10 · 今日第 8494 名
主要开发者
zllrunning

zllrunning/face-parsing.PyTorch 排名第 8,494，有 2,593 个星标。

同类别比较

zllrunning/face-parsing.PyTorch 排名第 8,494，此处有 8 个同类条目；baaivision/Painter 排名第 8,488。

同类别比较
名称排名指标
swz30/Restormer8,452
语言:
Python
星标数:
2,658
分叉数:
333
OmniSVG/OmniSVG8,463
语言:
Python
星标数:
2,642
分叉数:
108
简介:
[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.
microsoft/GLIP8,480
语言:
Python
星标数:
2,611
分叉数:
216
简介:
Grounded Language-Image Pre-training
baaivision/Painter8,488
语言:
Python
星标数:
2,600
分叉数:
180
简介:
Painter & SegGPT Series: Vision Foundation Models from BAAI
OFA-Sys/OFA8,516
语言:
Python
星标数:
2,552
分叉数:
249
简介:
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
X-PLUG/mPLUG-Owl8,523
语言:
Python
星标数:
2,540
分叉数:
190
简介:
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
VITA-MLLM/VITA8,528
语言:
Python
星标数:
2,538
分叉数:
183
简介:
✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
wgsxm/PartCrafter8,560
语言:
Python
星标数:
2,492
分叉数:
165
简介:
[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
关键参数与规格
关键参数与规格
参数值
语言Python
类别Models
子类别Vision models
星标数2,593
分叉数497
贡献者1
创建日期2019-04-18
更新日期2026-10-10
1 天星标数0
7 天星标数1
排名8,494
上次排名8,555
排名变化61
7 天星标排名9,335
上次 7 天星标排名7,788
7 天星标排名变化-1,547
总星标排名5,129
上次总星标排名5,122
总星标排名变化-7
国家China
README 摘录

PyTorch Contents Training Demo References Training 1. Train the model using CelebAMask-HQ dataset: Just run the train script: If you do not wish to train the model, you can download our pre-trained model and save it in . Evaluate the trained model using: Face makeup using parsing maps **face-makeup. PyTorch** Hair Lip Original Input Color References BiSeNet

常见问题

记录了多少星标和分叉？

zllrunning/face-parsing.PyTorch 有 2,593 个星标和 497 个分叉。

仓库排名是多少？

zllrunning/face-parsing.PyTorch 排名第 8,494。

记录的语言和类别是什么？

zllrunning/face-parsing.PyTorch 有 2,593 个星标，语言为 Python，类别为 Models。

哪个仓库排名最接近？

zllrunning/face-parsing.PyTorch 与 baaivision/Painter 比较，后者排名第 8,488，有 2,600 个星标。

README

face-parsing.PyTorch

[![](https://github.com/zllrunning/face-parsing.PyTorch/blob/master/6.jpg)](https://github.com/zllrunning/face-parsing.PyTorch)

Contents

Training

  1. Prepare training data: -- download CelebAMask-HQ dataset

    -- change file path in the prepropess_data.py and run

python prepropess_data.py
  1. Train the model using CelebAMask-HQ dataset: Just run the train script:
    $ CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 train.py

If you do not wish to train the model, you can download our pre-trained model and save it in res/cp.

Demo

  1. Evaluate the trained model using:
# evaluate using GPU
python test.py

Face makeup using parsing maps

face-makeup.PyTorch

 

Hair

Lip

Original Input

Color

References

排名相邻
同类项目