FastDup

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Implement Learning Efficient Convolutional Networks Through Network Slimming on YOLOX

Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding (CVPR2022)

The shared custom operator library for ONNXRuntime

High-Resolution Image Synthesis with Latent Diffusion Models

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Transformer related optimization, including BERT, GPT

Publicly released code for the LAMBERT model

Focal Inverse Distance Transform Maps for Crowd Localization and Counting in Dense Crowd

Minimal keyword extraction with BERT

PyTorch implementation of [1412.6553] and [1511.06530] tensor decomposition methods for convolutional layers.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Recovers passwords from pixelized screenshots

Learning Graph Normalization for Graph Neural Networks