Deeper DCGAN with AE stabilization

Last update: Feb 17, 2022

Related tags

Overview

AEGeAN

Deeper DCGAN with AE stabilization

Parallel training of generative adversarial network as an autoencoder with dedicated losses for each stage. Generator class has conditional .forward() method for enhanced ergonomics. Autoencoding pass seems to avoid mode collapse and recover faster if Generator is not doing well.

Has been used successfully with as few as ~200 images in the source folder.

Builds on the DCGAN PyTorch demo. This one generates images upto 1024x1024 so it can use a lot of VRAM.

Should work when the "dataroot" is configured ImageNet style: ".../a_dir_of_images/what_would_be_a_label" or ".../cat_pics/cute_cats/cat_001.jpg"

Have fun!

Examples of generated drawings here

Owner

Tyler Kvochick

tweeter: (at)tyler_kvochick

GitHub Repository

Sample and Computation Redistribution for Efficient Face Detection

Introduction SCRFD is an efficient high accuracy face detection approach which initially described in Arxiv. Performance Precision, flops and infer ti

13 Mar 05, 2022

Unofficial Implementation of MLP-Mixer, Image Classification Model

MLP-Mixer Unoffical Implementation of MLP-Mixer, easy to use with terminal. Train and test easly. https://arxiv.org/abs/2105.01601 MLP-Mixer is an arc

6 Dec 05, 2022

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation.

Understanding Minimum Bayes Risk Decoding This repo provides code and documentation for the following paper: Müller and Sennrich (2021): Understanding

13 May 01, 2022

Keras-tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation（Unfinished）

Keras-FCN Fully convolutional networks and semantic segmentation with Keras. Models Models are found in models.py, and include ResNet and DenseNet bas

645 Dec 29, 2022

Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors

SSL_OSC Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors

2 May 14, 2022

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

CNTK Chat Windows build status Linux build status The Microsoft Cognitive Toolkit (https://cntk.ai) is a unified deep learning toolkit that describes

17.3k Dec 29, 2022

Visual Adversarial Imitation Learning using Variational Models (VMAIL)

Visual Adversarial Imitation Learning using Variational Models (VMAIL) This is the official implementation of the NeurIPS 2021 paper. Project website

14 Nov 18, 2022

Keras community contributions

keras-contrib : Keras community contributions Keras-contrib is deprecated. Use TensorFlow Addons. The future of Keras-contrib: We're migrating to tens

1.6k Dec 21, 2022

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

PCAN for Multiple Object Tracking and Segmentation This is the offical implementation of paper PCAN for MOTS. We also present a trailer that consists

328 Dec 29, 2022

Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet.

Ravens is a collection of simulated tasks in PyBullet for learning vision-based robotic manipulation, with emphasis on pick and place. It features a Gym-like API with 10 tabletop rearrangement tasks,

367 Jan 09, 2023

Equipped customers with insights about their EVs Hourly energy consumption and helped predict future charging behavior using LSTM model

Equipped customers with insights about their EVs Hourly energy consumption and helped predict future charging behavior using LSTM model. Designed sample dashboard with insights and recommendation for

2 Apr 07, 2022

Deeper DCGAN with AE stabilization

Related tags

Overview

AEGeAN

Owner

Tyler Kvochick

Sample and Computation Redistribution for Efficient Face Detection

Unofficial Implementation of MLP-Mixer, Image Classification Model

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation.

Keras-tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation（Unfinished）

Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

Visual Adversarial Imitation Learning using Variational Models (VMAIL)

Keras community contributions

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet.

Equipped customers with insights about their EVs Hourly energy consumption and helped predict future charging behavior using LSTM model

The official PyTorch code implementation of "Human Trajectory Prediction via Counterfactual Analysis" in ICCV 2021.

Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions

Super Resolution for images using deep learning.

Torchyolo - Yolov3 ve Yolov4 modellerin Pytorch uygulamasıdır

Implementation for "Manga Filling Style Conversion with Screentone Variational Autoencoder" (SIGGRAPH ASIA 2020 issue)

Code for the Lovász-Softmax loss (CVPR 2018)

A synthetic texture-invariant dataset for object detection of UAVs

Multiple paper open-source codes of the Microsoft Research Asia DKI group

[WWW 2021] Source code for "Graph Contrastive Learning with Adaptive Augmentation"