Stars
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
[IJCAI18] SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…
[CVPR 2023] DepGraph: Towards Any Structural Pruning
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
A TensorFlow Implementation of the Transformer: Attention Is All You Need
《代码随想录》LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀
A nnie quantization aware training tool on pytorch.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
A Keras implementation of YOLOv3 (Tensorflow backend)
Object detection, 3D detection, and pose estimation using center point detection:
DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy
YoloV3 Implemented in Tensorflow 2.0
You Only Look One-level Feature (YOLOF), CVPR2021, Detectron2
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization
🙄 Difficult algorithm, Simple code.
Learning to See in the Dark. CVPR 2018
Tutorial code on how to build your own Deep Learning System in 2k Lines
Sourcetrail - free and open-source interactive source explorer
Pytorch implementation of DUT: Learning Video Stabilization by Simply Watching Unstable Videos
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark