Open deep learning compiler stack for cpu, gpu and specialized accelerators

学习音视频知识，整理资料，编写技术手册。

Support most of operator which convert mxnet to caffe.

Multi Model Server is a tool for serving neural net models for inference

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …

TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Code for 'Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting' in ECCV2018

Bounding Box Regression with Uncertainty for Accurate Object Detection (CVPR'19)

Pedestrian Detection Papers

Non-maximum suppression for object detection in a neural network

Cascade R-CNN forked from gluon-cv

yolact, fcos, gluoncv

Sandbox for training deep learning networks

Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)

Open-source code for paper "Dataset Distillation"

Official pytorch Implementation of Relational Knowledge Distillation, CVPR 2019

Codebase of the paper "Feature Intertwiner for Object Detection", ICLR 2019

Implementation of Data-free Knowledge Distillation for Deep Neural Networks (on arxiv!)

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.

Implementations of CVPR 2019 paper Distilling Object Detectors with Fine-grained Feature Imitation

Implementation of CVPR 2019 paper: Distilling Object Detectors with Fine-grained Feature Imitation

Distillation for faster rcnn in classification,regression,feature level,feature level +mask

Semi-supervised Adaptive Distillation is a model compression method for object detection.

The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

PyTorch implementation of "Distilling the Knowledge in a Neural Network" for model compression

Implements quantized distillation. Code for our paper "Model compression via distillation and quantization"