Stars
implement of SwiftNet:Real-time Video Object Segmentation
STMTrack: Template-free Visual Tracking with Space-time Memory Networks
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
A library to generate LaTeX expression from Python code.
A fully differentiable architecture search for GANs
[CVPR 2020] Code for paper "AdversarialNAS: Adversarial Neural Architecture Search for GANs".
High quality, fast, modular reference implementation of SSD in PyTorch
[ICCV 2019] "AutoGAN: Neural Architecture Search for Generative Adversarial Networks" by Xinyu Gong, Shiyu Chang, Yifan Jiang and Zhangyang Wang
Multinomial Distribution Learning for Effective Neural Architecture Search
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…
Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
An open-source toolbox for action understanding based on PyTorch
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
Object detection, 3D detection, and pose estimation using center point detection:
Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
OpenMMLab Detection Toolbox and Benchmark
MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.