Code for reproducing experiments in "Improved Training of Wasserstein GANs"

Last update: Jan 01, 2023

Related tags

Deep Learning improved_wgan_training

Overview

Improved Training of Wasserstein GANs

Code for reproducing experiments in "Improved Training of Wasserstein GANs".

Prerequisites

Python, NumPy, TensorFlow, SciPy, Matplotlib
A recent NVIDIA GPU

Models

Configuration for all models is specified in a list of constants at the top of the file. Two models should work "out of the box":

python gan_toy.py: Toy datasets (8 Gaussians, 25 Gaussians, Swiss Roll).
python gan_mnist.py: MNIST

For the other models, edit the file to specify the path to the dataset in DATA_DIR before running. Each model's dataset is publicly available; the download URL is in the file.

python gan_64x64.py: 64x64 architectures (this code trains on ImageNet instead of LSUN bedrooms in the paper)
python gan_language.py: Character-level language model
python gan_cifar.py: CIFAR-10

Owner

Ishaan Gulrajani

GitHub Repository

a practicable framework used in Deep Learning. So far UDL only provide DCFNet implementation for the ICCV paper (Dynamic Cross Feature Fusion for Remote Sensing Pansharpening)

UDL UDL is a practicable framework used in Deep Learning (computer vision). Benchmark codes, results and models are available in UDL, please contact @

11 Sep 30, 2022

Data and code from COVID-19 machine learning paper

Machine learning approaches for localized lockdown, subnotification analysis and cases forecasting in São Paulo state counties during COVID-19 pandemi

4 Dec 22, 2022

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

Memory Efficient Attention Pytorch Implementation of a memory efficient multi-head attention as proposed in the paper, Self-attention Does Not Need O(

180 Jan 05, 2023

A deep learning CNN model to identify and classify and check if a person is wearing a mask or not.

Face Mask Detection The Model is designed to check if any human is wearing a mask or not. Dataset Description The Dataset contains a total of 11,792 i

1 Mar 01, 2022

Towhee is a flexible machine learning framework currently focused on computing deep learning embeddings over unstructured data.

1.7k Jan 08, 2023

Code for reproducing experiments in "Improved Training of Wasserstein GANs"

Related tags

Overview

Improved Training of Wasserstein GANs

Prerequisites

Models

Owner

Ishaan Gulrajani

a practicable framework used in Deep Learning. So far UDL only provide DCFNet implementation for the ICCV paper (Dynamic Cross Feature Fusion for Remote Sensing Pansharpening)

Data and code from COVID-19 machine learning paper

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

A deep learning CNN model to identify and classify and check if a person is wearing a mask or not.

Towhee is a flexible machine learning framework currently focused on computing deep learning embeddings over unstructured data.

Lazy, a tool for running things in idle time

Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper

Active and Sample-Efficient Model Evaluation

ML-Decoder: Scalable and Versatile Classification Head

A motion detection system with RaspberryPi, OpenCV, Python

Tensorflow implementation of our method: "Triangle Graph Interest Network for Click-through Rate Prediction".

A Web API for automatic background removal using Deep Learning. App is made using Flask and deployed on Heroku.

clustering moroccan stocks time series data using k-means with dtw (dynamic time warping)

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

QAT(quantize aware training) for classification with MQBench

Simulator for FRC 2022 challenge: Rapid React

Planning from Pixels in Environments with Combinatorially Hard Search Spaces -- NeurIPS 2021

Ascend your Jupyter Notebook usage

🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)

A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon.