A Comprehensive Toolkit for High-Quality PDF Content Extraction

Chinese version of GPT2 training code, using BERT tokenizer.

Open-Sora: Democratizing Efficient Video Production for All

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

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

🧑‍🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cycle…

Text to Video Generation Problem

This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".

人像卡通化探索项目 (photo-to-cartoon translation project)

This repository implements the the encoder and decoder model with attention model for OCR

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Image-to-Image Translation in PyTorch

Official Pytorch implementation of "DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network" (CVPR'21)

LPIPS metric. pip install lpips

Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis

Learning diverse image-to-image translation from unpaired data

Toward Multimodal Image-to-Image Translation

pandas学习课程代码仓库

BIgGAN implementation by TensorFlow 2.0 RC-version

Seeing what a GAN cannot generate. Visualizes and quantifies object classes within scenes that are outside the range of a GAN.

Transforms for video datasets in pytorch

MSGAN: Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis (CVPR2019)