znxlwm / Pytorch Pix2pix
Pytorch implementation of pix2pix for various datasets.
Stars: ✭ 74
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pytorch Pix2pix
Psgan
Periodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (+45.95%)
Mutual labels: gan, generative-model, generative-adversarial-networks
Unit
Unsupervised Image-to-Image Translation
Stars: ✭ 1,809 (+2344.59%)
Mutual labels: gan, pix2pix, image-translation
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (+31.08%)
Mutual labels: gan, generative-model, image-translation
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 (+145.95%)
Mutual labels: gan, pix2pix, generative-adversarial-networks
pix2pix-tensorflow
A minimal tensorflow implementation of pix2pix (Image-to-Image Translation with Conditional Adversarial Nets - https://phillipi.github.io/pix2pix/).
Stars: ✭ 22 (-70.27%)
Mutual labels: gan, pix2pix, image-translation
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+5014.86%)
Mutual labels: gan, generative-model, generative-adversarial-networks
Gdwct
Official PyTorch implementation of GDWCT (CVPR 2019, oral)
Stars: ✭ 122 (+64.86%)
Mutual labels: gan, generative-adversarial-networks, image-translation
Munit
Multimodal Unsupervised Image-to-Image Translation
Stars: ✭ 2,404 (+3148.65%)
Mutual labels: gan, pix2pix, image-translation
Cyclegan
PyTorch implementation of CycleGAN
Stars: ✭ 38 (-48.65%)
Mutual labels: gan, generative-adversarial-networks, image-translation
cgan-face-generator
Face generator from sketches using cGAN (pix2pix) model
Stars: ✭ 52 (-29.73%)
Mutual labels: gan, generative-model, pix2pix
Segan
Speech Enhancement Generative Adversarial Network in TensorFlow
Stars: ✭ 661 (+793.24%)
Mutual labels: gan, generative-model, generative-adversarial-networks
Generative Models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Stars: ✭ 6,701 (+8955.41%)
Mutual labels: gan, generative-model
Frechet Inception Distance
CPU/GPU/TPU implementation of the Fréchet Inception Distance
Stars: ✭ 66 (-10.81%)
Mutual labels: gan, generative-model
Delving Deep Into Gans
Generative Adversarial Networks (GANs) resources sorted by citations
Stars: ✭ 834 (+1027.03%)
Mutual labels: generative-model, generative-adversarial-networks
Csmri Refinement
Code for "Adversarial and Perceptual Refinement Compressed Sensing MRI Reconstruction"
Stars: ✭ 21 (-71.62%)
Mutual labels: gan, generative-adversarial-networks
Adversarialnetspapers
Awesome paper list with code about generative adversarial nets
Stars: ✭ 6,219 (+8304.05%)
Mutual labels: gan, image-translation
Began Tensorflow
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"
Stars: ✭ 904 (+1121.62%)
Mutual labels: gan, generative-model
Dcgan Tensorflow
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
Stars: ✭ 6,963 (+9309.46%)
Mutual labels: gan, generative-model
Image To Image Papers
🦓<->🦒 🌃<->🌆 A collection of image to image papers with code (constantly updating)
Stars: ✭ 949 (+1182.43%)
Mutual labels: gan, image-translation
Discogan Pytorch
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
Stars: ✭ 961 (+1198.65%)
Mutual labels: gan, generative-model
pytorch-pix2pix
Pytorch implementation of pix2pix [1] for various datasets.
- you can download datasets: https://people.eecs.berkeley.edu/~tinghuiz/projects/pix2pix/datasets/
- you can see more information for network architecture and training details in https://arxiv.org/pdf/1611.07004.pdf
dataset
- cityscapes
- 2,975 training images, 200 train epochs, 1 batch size, inverse order: True
- facades
- 400 training images, 200 train epochs, 1 batch size, inverse order: True
- maps
- 1,096 training images, 200 train epochs, 1 batch size, inverse order: True
- edges2shoes
- 50k training images, 15 train epochs, 4 batch size, inverse order: False
- edges2handbags
- 137k training images, 15 train epochs, 4 batch size, inverse order: False
Resutls
cityscapes
- cityscapes after 200 epochs
- First column: input, second column: output, third column: ground truth
- Generate animation for fixed inputs
- Learning Time
- cityscapes pix2pix - Avg. per epoch: 332.08 sec; Total 200 epochs: 66,846.58 sec
facades
- facades after 200 epochs
- First column: input, second column: output, third column: ground truth
- Generate animation for fixed inputs
- Learning Time
- facades pix2pix - Avg. per epoch: 44.94 sec; Total 200 epochs: 9,282.64 sec
edges2handbags
- edges2handbags after 15 epochs
- First column: input, second column: output, third column: ground truth
- Generate animation for fixed inputs
- Learning Time
- edges2handbags pix2pix - Avg. per epoch: 10,228.08 sec; Total 15 epochs: 153,443.62 sec
Development Environment
- Ubuntu 14.04 LTS
- NVIDIA GTX 1080 ti
- cuda 8.0
- Python 2.7.6
- pytorch 0.1.12
- matplotlib 1.3.1
- imageio 2.2.0
- scipy 0.19.1
Reference
[1] Isola, Phillip, et al. "Image-to-image translation with conditional adversarial networks." arXiv preprint arXiv:1611.07004 (2016).
(Full paper: https://arxiv.org/pdf/1611.07004.pdf)
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].