[CVPR2020] Adversarial Latent Autoencoders

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

A procedural Blender pipeline for photorealistic training image generation

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

ResNeSt: Split-Attention Networks

Mask RCNN in TensorFlow

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

PyTorch original implementation of Cross-lingual Language Model Pretraining.

The author's officially unofficial PyTorch BigGAN implementation.

Models and examples built with TensorFlow

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Dense Prediction Transformers

Use supervised learning to illuminate the latent space of GAN for controlled generation and edit

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

Compare GAN code.

Nvidia Semantic Segmentation monorepo

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch

Faster RCNN with PyTorch

[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

Tensorflow implementation of contextualized word representations from bi-directional language models

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

[CVPR 2020] Interpreting the Latent Space of GANs for Semantic Face Editing

Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to …

🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

PixelNeRF Official Repository

disentanglement_lib is an open-source library for research on learning disentangled representations.

Generative Adversarial Transformers

Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018