atranitell

gallery

Flutter Gallery was a resource to help developers evaluate and use Flutter

flutter_desktop_challenges

vega

AutoML tools chain

oneflow

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

PaddleSlim

PaddleSlim is an open-source library for deep model compression and architecture search.

cmake-optimize-architecture-flag

CMake module to optimize cflags for architecture extensions such as SSE, AVX

micronet

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-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

cnn-quantization

Quantization of Convolutional Neural networks.

Ultra-Fast-Lane-Detection

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

apps

A collection of apps built on Electron

electron-react-boilerplate

A Foundation for Scalable Cross-Platform Apps

Arm-neon-intrinsics

arm neon 相关文档和指令意义

dabnn

dabnn is an accelerated binary neural networks inference framework for mobile platform

HashNet

Code release for "HashNet: Deep Learning to Hash by Continuation" (ICCV 2017)

DeepHash

An Open-Source Package for Deep Learning to Hash (DeepHash)

hashing-baseline-for-image-retrieval

:octocat:Various hashing methods for image retrieval and serves as the baselines

google-research

Google Research

Knowledge-Distillation-Zoo

Pytorch implementation of various Knowledge Distillation (KD) methods.

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

research-ms-loss

MS-Loss: Multi-Similarity Loss for Deep Metric Learning

bus-segmentation

MATLAB implementation to segment breast lesions in ultrasound images (ICIAR 2016)

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

UniSIMD-assembler

SIMD macro assembler unified for ARM, MIPS, PPC and x86

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

torchprof

PyTorch layer-by-layer model profiler

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.

hardware-effects-gpu

Demonstration of various hardware effects on CUDA GPUs.

dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

FCOS_PLUS

Some improvements (center sample) about FCOS (FCOS: Fully Convolutional One-Stage Object Detection).