zhengyima / Deepnude_nowatermark_withmodel
Licence: mit
DeepNude source code,without watermark,with demo and model download link,one command to run offline,GAN/Pytorch/pix2pix/pic2pic
Stars: ✭ 950
Programming Languages
Projects that are alternatives of or similar to Deepnude nowatermark withmodel
Anonymize Video
Replace faces in a video with imaginary persons generated by a progressive GAN deep neural network
Stars: ✭ 15 (-98.42%)
Mutual labels: opencv, gan
Paddlegan
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.
Stars: ✭ 4,987 (+424.95%)
Mutual labels: gan, pix2pix
Pose2pose
This is a pix2pix demo that learns from pose and translates this into a human. A webcam-enabled application is also provided that translates your pose to the trained pose. Everybody dance now !
Stars: ✭ 182 (-80.84%)
Mutual labels: gan, pix2pix
Deblurgan
Image Deblurring using Generative Adversarial Networks
Stars: ✭ 2,033 (+114%)
Mutual labels: gan, pix2pix
cgan-face-generator
Face generator from sketches using cGAN (pix2pix) model
Stars: ✭ 52 (-94.53%)
Mutual labels: gan, pix2pix
Cyclegan Vc2
Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2
Stars: ✭ 158 (-83.37%)
Mutual labels: gan, pix2pix
Swapnet
Virtual Clothing Try-on with Deep Learning. PyTorch reproduction of SwapNet by Raj et al. 2018. Now with Docker support!
Stars: ✭ 202 (-78.74%)
Mutual labels: gan, pix2pix
pix2pix-tensorflow
A minimal tensorflow implementation of pix2pix (Image-to-Image Translation with Conditional Adversarial Nets - https://phillipi.github.io/pix2pix/).
Stars: ✭ 22 (-97.68%)
Mutual labels: gan, pix2pix
Pix2pixbegan.pytorch
A pytorch implementation of pix2pix + BEGAN (Boundary Equilibrium Generative Adversarial Networks)
Stars: ✭ 148 (-84.42%)
Mutual labels: gan, pix2pix
Pix2pixhd
Synthesizing and manipulating 2048x1024 images with conditional GANs
Stars: ✭ 5,553 (+484.53%)
Mutual labels: gan, pix2pix
Pix2pix Film
An implementation of Pix2Pix in Tensorflow for use with frames from films
Stars: ✭ 162 (-82.95%)
Mutual labels: gan, pix2pix
Tensorflow Pix2pix
A lightweight pix2pix Tensorflow implementation.
Stars: ✭ 143 (-84.95%)
Mutual labels: gan, pix2pix
Munit
Multimodal Unsupervised Image-to-Image Translation
Stars: ✭ 2,404 (+153.05%)
Mutual labels: gan, pix2pix
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (-85.16%)
Mutual labels: gan, pix2pix
Pytorch Cyclegan And Pix2pix
Image-to-Image Translation in PyTorch
Stars: ✭ 16,477 (+1634.42%)
Mutual labels: gan, pix2pix
Igan
Interactive Image Generation via Generative Adversarial Networks
Stars: ✭ 3,845 (+304.74%)
Mutual labels: gan, pix2pix
DeepNude
DeepNude Source Code
DeepNude源代码
去水印
带三个模型.lib文件下载地址
供广大程序员技术交流使用
demo地址: demo很原始脆弱不鲁棒,所以感兴趣的话尽量还是自己去跑代码吧。不要对demo做坏事哦,不然就关掉= =
Preinstallation
Before launch the script install these packages in your Python3 environment:
- numpy
- Pillow
- setuptools
- six
- pytorch
- torchvision
- wheel
pip3 install numpy pillow setuptools six pytorch torchvision wheel
建议使用Conda安装 :)
conda create -n deepnude python=3.6 numpy Pillow setuptools six pytorch torchvision wheel
conda activate deepnude
注:如果懒得折腾Python环境,也可以使用docker一键运行,见下
感谢网友飞哥提供docker一键运行部分技术支持
使用docker一键运行
cd ~
git clone https://github.com/zhengyima/DeepNude_NoWatermark_withModel.git --depth 1 deepnude
cd deepnude
docker run --rm -it -v $PWD:/app:rw ababy/python-deepnude /bin/bash
python main.py
注意: docker运行只能使用cpu,所以,需要修改gpu运行为cpu, 修改方法请参考 #GPU. 实际运行速度也慢不了多少.
对应的三个 .lib 文件需要自己手动下载后, 添加到项目根目录
checkpoints
目录下, 才能正常运行, 由于文件太大, 就没有放入docker镜像
Models
在运行之前需下载三个.lib文件,之后在项目根目录下新建checkpoints目录,将下载的三个文件放至checkpoints目录下。
友情提供以下两种下载渠道:
Launch the script
环境配好,模型下好之后便可以运行代码了!
python main.py
The script will transform input.png to output.png.
GPU
本项目默认使用id为0的GPU运行。
若运行环境不带GPU,则报错。如果没有GPU或想使用CPU运行程序,请将gan.py中
self.gpu_ids = [0] #FIX CPU
改为 (
self.gpu_ids = [] #FIX CPU
Links
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].