Implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

Last update: Nov 10, 2022

Related tags

Overview

SinGAN

This is an unofficial implementation of SinGAN from someone who's been sitting right next to SinGAN's creator for almost five years.

Please refer the project's page for more details.

Citation

If you use this code for your research, please cite the paper:

@inproceedings{shaham2019singan,
  title={Singan: Learning a generative model from a single natural image},
  author={Shaham, Tamar Rott and Dekel, Tali and Michaeli, Tomer},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={4570--4580},
  year={2019}
}

Code

Clone repository

Clone this repository into any place you want.

git clone https://github.com/kligvasser/SinGAN
cd ./SinGAN/generation/

Install dependencies

python -m pip install -r requirements.txt

This code tested in PyTorch 1.8.1.

Training

To train SinGAN model on your own image:

python3 main.py --root <path-to-image>

Evaluating

For evaluating, run the following command:

python3 main.py --root <path-to-image> --evaluation --model-to-load <path-to-model-pt> --amps-to-load <path-to-amp-pt> --num-steps <number-of-samples> --batch-size <number-of-images-in-batch>

Implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

Related tags

Overview

SinGAN

Citation

Code

Clone repository

Install dependencies

Training

Evaluating

Owner

Finding an Unsupervised Image Segmenter in each of your Deep Generative Models

A flexible submap-based framework towards spatio-temporally consistent volumetric mapping and scene understanding.

Largest list of models for Core ML (for iOS 11+)

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

Evaluation toolkit of the informative tracking benchmark comprising 9 scenarios, 180 diverse videos, and new challenges.

Godot RL Agents is a fully Open Source packages that allows video game creators

Implementation of the Swin Transformer in PyTorch.

Marvis is Mastouri's Jarvis version of the AI-powered Python personal assistant.

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

P-Tuning v2: Prompt Tuning Can Be Comparable to Finetuning Universally Across Scales and Tasks

NOMAD - A blackbox optimization software

DeepLabv3+：Encoder-Decoder with Atrous Separable Convolution语义分割模型在tensorflow2当中的实现

Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Source Code

Jittor implementation of Recursive-NeRF: An Efficient and Dynamically Growing NeRF

PyTorch implementation of Histogram Layers from DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation

Official implementation of ACMMM'20 paper 'Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework'

CLIP (Contrastive Language–Image Pre-training) for Italian

A higher performance pytorch implementation of DeepLab V3 Plus(DeepLab v3+)

SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

multimodal transformer