zhangjunh / Dr Gan By Pytorch
An implement of Disentangled Representation Learning GAN for Pose-Invariant Face Recognition
Stars: ✭ 106
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Dr Gan By Pytorch
Face Generator
Generate human faces with neural networks
Stars: ✭ 266 (+150.94%)
Mutual labels: gan, face
Anime Face Gan Keras
A DCGAN to generate anime faces using custom mined dataset
Stars: ✭ 161 (+51.89%)
Mutual labels: gan, face
Apdrawinggan
Code for APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs (CVPR 2019 Oral)
Stars: ✭ 510 (+381.13%)
Mutual labels: gan, face
Gan Mnist
Generative Adversarial Network for MNIST with tensorflow
Stars: ✭ 193 (+82.08%)
Mutual labels: gan, face
Anonymize Video
Replace faces in a video with imaginary persons generated by a progressive GAN deep neural network
Stars: ✭ 15 (-85.85%)
Mutual labels: gan, face
Generative Models
Comparison of Generative Models in Tensorflow
Stars: ✭ 96 (-9.43%)
Mutual labels: gan
Lsd Seg
Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
Stars: ✭ 99 (-6.6%)
Mutual labels: gan
Unified Gan Tensorflow
A Tensorflow implementation of GAN, WGAN and WGAN with gradient penalty.
Stars: ✭ 93 (-12.26%)
Mutual labels: gan
Sprint gan
Privacy-preserving generative deep neural networks support clinical data sharing
Stars: ✭ 92 (-13.21%)
Mutual labels: gan
Fagan
A variant of the Self Attention GAN named: FAGAN (Full Attention GAN)
Stars: ✭ 105 (-0.94%)
Mutual labels: gan
Tensorflow2.0 Examples
🙄 Difficult algorithm, Simple code.
Stars: ✭ 1,397 (+1217.92%)
Mutual labels: gan
Torchelie
Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.
Stars: ✭ 98 (-7.55%)
Mutual labels: gan
Doppelganger
[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
Stars: ✭ 97 (-8.49%)
Mutual labels: gan
Zerospeech Tts Without T
A Pytorch implementation for the ZeroSpeech 2019 challenge.
Stars: ✭ 100 (-5.66%)
Mutual labels: gan
Tbgan
Project Page of 'Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks'
Stars: ✭ 105 (-0.94%)
Mutual labels: gan
Dped
Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks
Stars: ✭ 1,315 (+1140.57%)
Mutual labels: gan
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (-8.49%)
Mutual labels: gan
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-5.66%)
Mutual labels: gan
3d Gan Superresolution
3D super-resolution using Generative Adversarial Networks
Stars: ✭ 97 (-8.49%)
Mutual labels: gan
DR-GAN-by-pytorch
Disentangled Representation Learning GAN for Pose-Invariant Face Recognition
- Authors: Luan Tran, Xi Yin, Xiaoming Liu
- CVPR2017: http://cvlab.cse.msu.edu/pdfs/Tran_Yin_Liu_CVPR2017.pdf
- Pytorch implimentation of DR-GAN (updated version in "Representation Learning by Rotating Your Faces")
- Added a pretrained ResNet18 to offer a feature loss in order to improve Generator's performance. (Only in Multi_DRGAN)
Requirements
- python 3.x
- pytorch 0.2
- torchvision
- numpy
- scipy
- matplotlib
- pillow
- tensorboardX
How to use
Single-Image DR-GAN
-
Modify model function at base_options.py to define single model.
- Data needs to have ID and pose lables corresponds to each image.
- If you don't have, default dataset is CFP_dataset. Modify dataroot function at base_options.py.
-
Run train.py to train models
- Trained models and Loss_log will be saved at "checkpoints" by default. Generated pictures will be saved at "result".
python train.py
- You can also use tensorboard to watch the loss graphs in real-time. (Install tensorboard before doing it.)
tensorboard --logdir=/home/zhangjunhao/logs (Or the address of dir 'logs' in your folder.）
-
Generate Image with arbitrary pose
- Change the "save_path" in base_model.py.
- Specify leaned model's filename by "--pretrained_G" option in base_options.py.
- Generated images will be saved at specified result directory.
python test.py
Multi-Image DR-GAN
-
Modify model function at base_options.py to define multi model.
- Data needs to have ID and pose lables corresponds to each image.
- If you don't have, default dataset is CFP_dataset. Modify dataroot function at base_options.py.
-
Run train.py to train models
- Trained models and Loss_log will be saved at "checkpoints" by default. Generated pictures will be saved at "result".
python train.py
- You can also use tensorboard to watch the loss graphs in real-time. (Install tensorboard before doing it.)
tensorboard --logdir=/home/zhangjunhao/logs (Or the address of dir 'logs' in your folder.）
-
Generate Image with arbitrary pose
- Change the "save_path" in base_model.py.
- Specify leaned model's filename by "--pretrained_G" option in base_options.py.
- Generated images will be saved at specified result directory.
python test.py
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].