speedup4dl Goto Github PK

awesome-knowledge-distillation

Awesome Knowledge Distillation

biprop

Identify a binary weight or binary weight and activation subnetwork within a randomly initialized network by only pruning and binarizing the network.

caffe

Caffe for Sparse and Low-rank Deep Neural Networks

caffe-shufflenet

This is re-implementation of "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices"

caffemodelcompression

Tool to compress trained caffe weights

centripetal-sgd

Codes of Centripetal SGD

channel-pruning

Channel Pruning for Accelerating Very Deep Neural Networks

deep-compression-alexnet

Deep Compression on AlexNet

distilling-nn

Tensorflow implementation of Distilling the Knowledge in a Neural Network

distilling-the-knowledge-in-neural-network

Teaches a student network from the knowledge obtained via training of a larger teacher network

fisherpruning

Group Fisher Pruning for Practical Network Compression(ICML2021)

flowandprune

Code repository for the paper "A Gradient Flow Framework for Analyzing Network Pruning"

image-compression-cnn

Semantic JPEG image compression using deep convolutional neural network (CNN)

low-rank-bilinear-pooling

Fine-grained classification with powerful second order statistics in a compact end-to-end trainable model (low rank bilinear pooling for fine-grained classification)

lowrankcnn

Low-rank convolutional neural networks

mnist_distilling_john

reproduce 《Distilling the Knowledge in a Neural Network》

model_compression

Implementation of model compression with knowledge distilling method.

modelcompression-2019

msdnet

Multi-Scale Dense Convolutional Networks for Efficient Prediction

permute-quantize-finetune

Using ideas from product quantization for state-of-the-art neural network compression.

samplecaffemodelcompression

This is a really simple compression of Caffe Model

squeezenet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

thinet

caffe model of ICCV'17 paper - ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression https://arxiv.org/abs/1707.06342

torchprune

A research library for pytorch-based neural network pruning, compression, and more.

versatile-filters

Pytorch code for paper: Learning Versatile Filters for Efficient Convolutional Neural Networks (NeurIPS 2018)

vgg-or-mobilenet-ssd

Caffe implementation of Google VGG/MobileNet/ShuffleNet SSD detection network. Ref: (https://github.com/chuanqi305/MobileNet-SSD) (https://github.com/weiliu89/caffe)