https://github.com/kirili4ik/pix2pix-pytorch

Pix2Pix model written in PyTorch
https://github.com/kirili4ik/pix2pix-pytorch

gan pix2pix pix2pix-pytorch pytorch

Last synced: 3 months ago
JSON representation

Pix2Pix model written in PyTorch

• Host: GitHub
• URL: https://github.com/kirili4ik/pix2pix-pytorch
• Owner: Kirili4ik
• Created: 2020-12-14T19:02:33.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2021-03-19T10:48:34.000Z (about 4 years ago)
• Last Synced: 2025-01-20T18:46:21.718Z (5 months ago)
• Topics: gan, pix2pix, pix2pix-pytorch, pytorch
• Language: Jupyter Notebook
• Homepage:
• Size: 6.16 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Pix2Pix model in PyTorch

This repository is an implementation of model described in [Pix2Pix (Isola et al., 2016)](https://arxiv.org/pdf/1611.07004.pdf). 

The task is to translate picture to a different modality (e.g. day photo to night one) using conditional GAN. Model was trained on facades and day2night datasets. Those can be found [here](http://efrosgans.eecs.berkeley.edu/pix2pix/datasets/).

There are some good examples of trained models:

![alt text](https://github.com/Kirili4ik/pix2pix-pytorch/blob/main/Experiments/facades.png "facades")

![alt text](https://github.com/Kirili4ik/pix2pix-pytorch/blob/main/Experiments/d2n.png "d2n")

Also there were some discoveries and experiements, e.g.:

![alt text](https://github.com/Kirili4ik/pix2pix-pytorch/blob/main/Experiments/exp.png "augmentations-vs-no_augmentations")

On the picture above dashed line represents loss on validation set. It's clearly seen that augmentations help to avoid overfitting.

More experiements can be found in my [report](https://github.com/Kirili4ik/pix2pix-pytorch/blob/main/Experiments/Experiments.pdf) (in Russian).