All Projects → yunjey → Domain Transfer Network

yunjey / Domain Transfer Network

Licence: mit
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Domain Transfer Network

Oneshottranslation
Pytorch implementation of "One-Shot Unsupervised Cross Domain Translation" NIPS 2018
Stars: ✭ 135 (-84.12%)
Mutual labels:  unsupervised-learning, image-generation
Distancegan
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017
Stars: ✭ 180 (-78.82%)
Mutual labels:  unsupervised-learning, image-generation
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (-39.65%)
Mutual labels:  unsupervised-learning, image-generation
Athena
an open-source implementation of sequence-to-sequence based speech processing engine
Stars: ✭ 542 (-36.24%)
Mutual labels:  unsupervised-learning
Unsupervised Classification
SCAN: Learning to Classify Images without Labels (ECCV 2020), incl. SimCLR.
Stars: ✭ 605 (-28.82%)
Mutual labels:  unsupervised-learning
Awesome Artificial Intelligence
A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.
Stars: ✭ 6,516 (+666.59%)
Mutual labels:  unsupervised-learning
Multi Viewpoint Image Generation
Given an image and a target viewpoint, generate synthetic image in the target viewpoint
Stars: ✭ 23 (-97.29%)
Mutual labels:  image-generation
Lemniscate.pytorch
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Stars: ✭ 532 (-37.41%)
Mutual labels:  unsupervised-learning
Contrastive Unpaired Translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
Stars: ✭ 822 (-3.29%)
Mutual labels:  image-generation
Mixnmatch
Pytorch implementation of MixNMatch
Stars: ✭ 694 (-18.35%)
Mutual labels:  image-generation
Data Efficient Gans
[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training
Stars: ✭ 682 (-19.76%)
Mutual labels:  image-generation
Graph2vec
A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).
Stars: ✭ 605 (-28.82%)
Mutual labels:  unsupervised-learning
Simclr
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
Stars: ✭ 750 (-11.76%)
Mutual labels:  unsupervised-learning
Pytorch Cyclegan
A clean and readable Pytorch implementation of CycleGAN
Stars: ✭ 558 (-34.35%)
Mutual labels:  image-generation
Bagofconcepts
Python implementation of bag-of-concepts
Stars: ✭ 18 (-97.88%)
Mutual labels:  unsupervised-learning
Context Encoder
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
Stars: ✭ 731 (-14%)
Mutual labels:  unsupervised-learning
Variational Autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)
Stars: ✭ 807 (-5.06%)
Mutual labels:  unsupervised-learning
Malnyun faces
침착한 생성모델 학습기
Stars: ✭ 677 (-20.35%)
Mutual labels:  image-generation
All About The Gan
All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN
Stars: ✭ 630 (-25.88%)
Mutual labels:  unsupervised-learning
Summary loop
Codebase for the Summary Loop paper at ACL2020
Stars: ✭ 26 (-96.94%)
Mutual labels:  unsupervised-learning

Domain Transfer Network (DTN)

TensorFlow implementation of Unsupervised Cross-Domain Image Generation. alt text

Requirements


Usage

Clone the repository

$ git clone https://github.com/yunjey/dtn-tensorflow.git
$ cd dtn-tensorflow

Download the dataset

$ chmod +x download.sh
$ ./download.sh

Resize MNIST dataset to 32x32

$ python prepro.py

Pretrain the model f

$ python main.py --mode='pretrain'

Train the model G and D

$ python main.py --mode='train'

Transfer SVHN to MNIST

$ python main.py --mode='eval'

Results

From SVHN to MNIST

alt text

alt text

alt text

alt text

From Photos to Emoji (in paper)

alt text

alt text

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].