32l / Neural-Network-Model-Compressing
Caffe implementation of Dynamic Network Surgery and Incremental Network Quantization
☆15Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for Neural-Network-Model-Compressing
- Two-Step Quantization on AlexNet☆13Updated 6 years ago
- Android demo for dabnn☆20Updated 5 years ago
- Caffe implementation of Optimal-Ternary-Weights-Approximation in "Two-Step Quantization for Low-bit Neural Networks" (CVPR2018).☆14Updated 6 years ago
- A caffe implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.☆52Updated 6 years ago
- A script to convert floating-point CNN models into generalized low-precision ShiftCNN representation☆55Updated 7 years ago
- A tool to count operators and parameters of your MXNet-Gluon model.☆21Updated 4 years ago
- ☆42Updated 4 years ago
- Added quantization layer into caffe (support a coarse level fixed point simulation)☆22Updated 7 years ago
- Merge convolution and batchnorm layers in both Caffe and PyTorch using Python☆18Updated 5 years ago
- Caffe implementation of ICCV 2017 & TPAMI 2018 paper - ThiNet☆46Updated 6 years ago
- This repo is re-produce for Channel_pruning☆11Updated 6 years ago
- Implement Towards Effective Low-bitwidth Convolutional Neural Networks☆42Updated 6 years ago
- ☆45Updated 5 years ago
- Apply the pruning strategy for MobileNet_v2☆51Updated 5 years ago
- convert tensorflow mobilenet-v2 checkpoint to caffemodel☆30Updated 5 years ago
- Caffe Computation Graph Optimization.☆29Updated 4 years ago
- ☆9Updated 5 years ago
- This repository represents training examples for the CVPR 2018 paper "SYQ:Learning Symmetric Quantization For Efficient Deep Neural Netwo…☆32Updated 5 years ago
- caffe implement☆23Updated 3 years ago
- This repo contains code for *FD-MobileNet: Improved MobileNet with A Fast Downsampling Strategy*.☆34Updated 6 years ago
- Simulate quantization and quantization aware training for MXNet-Gluon models.☆46Updated 4 years ago
- Model shared. Top1:67.408/Top5:87.258☆48Updated 6 years ago
- Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions (in Caffe)☆34Updated 6 years ago
- This is caffe implementation of shuffleNet V2☆69Updated 6 years ago
- ☆87Updated 6 years ago
- Caffe: a fast open framework for deep learning.☆27Updated 7 years ago
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers https://arxiv.org/abs/1802.00124☆71Updated 6 years ago
- Modified RefineDet☆23Updated 4 years ago