liuheng92

ControlNet

Let us control diffusion models!

ControlNet-v1-1-nightly

Nightly release of ControlNet 1.1

generative-models

Generative Models by Stability AI

intrinsic-dimension

LDES

[AAAI19] Robust Estimation of Similarity Transformation for Visual Object Tracking

LDESCpp

This is a C++ implementation of AAAI2019 paper LDES tracker. Now branch square is available, which uses square templates

pyCFTrackers

Python re-implementation of some correlation filter based tracker

TBCF

Tracking Benchmark for Correlation Filters

benchmark_results

Visual Tracking Paper List

CppMT

CMT

LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Torch-Pruning

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

FLAME_PyTorch

This is a implementation of the 3D FLAME model in PyTorch

Deep3DFaceReconstruction

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)

SEAN

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)

face-parsing.PyTorch

Using modified BiSeNet for face parsing in PyTorch

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

mcan-vqa

Deep Modular Co-Attention Networks for Visual Question Answering

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

neuraltalk2

Efficient Image Captioning code in Torch, runs on GPU

opencv

Open Source Computer Vision Library

YOWO

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

MOC-Detector

[ECCV 2020] Actions as Moving Points

pytorchvideo

A deep learning library for video understanding research.

RFNext

RF-Next: Efficient Receptive Field Search for CNN(TPAMI2022, CVPR2021) Try it, you wouldn't regret it!

Savior

(WIP)The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework for algorithm service that ensures reliability, high concurrency and scalability of services.

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark