Projects sharing features with ThiNet

This repository contains the code for reproducing the results, and trained ImageNet models, in the following paper:

Open source code for our ECCV2022 accepted paper. https://link.springer.com/chapter/10.1007/978-3-031-20050-2_29

Haoran You, Baopu Li, Zhanyi Sun, Xu Ouyang, Yingyan Lin

We use the template from https://github.com/ashleve/lightning-hydra-template. Please read the instructions there to understand the repo structure.

CVPR 2019 Oral.

The PyTorch implementation for our IJCAI 2018 paper. This implementation is based on ResNeXt-DenseNet.

This repository is the official implementation of Winning the Lottery Ahead of Time: Efficient Early Network Pruning published at ICML 2022.

By Liyang Liu\, Shilong Zhang\, Zhanghui Kuang, Jing-Hao Xue, Aojun Zhou, Xinjiang Wang, Yimin Chen, Wenming Yang, Qingmin Liao, Wayne Zhang

This is the pytorch implementation of our paper "MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning", https://arxiv.org/abs/1903.10258, published in ICCV 2019.

Main contributors of this code base: Lucas Liebenwein, Cenk Baykal.

Code to reproduce results of the paper Data-Efficient Structured Pruning via Submodular Optimization

Reference ImageNet implementation of SelecSLS Convolutional Neural Network architecture proposed in XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera (SIGGRAPH 2020).

&nbsp &nbsp

This repository is the official PyTorch implementation of NeurIPS 2022 paper Structural Pruning via Latency-Saliency Knapsack.

Figure 1: Top-1 accuracy tradeoff curve for pruning ResNet50 on the ImageNet classification dataset using a latency cost constraint. Baseline is from PyTorch model hub. Accuracy against FPS speed (left) and FLOPs (right) show the benefit of our method, particularly at high pruning ratios. For…

This is a code package as part of "Plant ’n’ Seek: Can You Find the Winning Ticket?" by Jonas Fischer and Rebekka Burkholz.

Code accompanying the paper "On the Existence of Universal Lottery Tickets" (ICLR 2022)

2019.05.10: We release a new version of dcp.

PyTorch implementation for GAL.

2021/01/08: This new version supports pruning with multi-GPU training. Code for pruning the torchvision standard ResNet-50 is released. The old version is moved into the "deprecated" directory.

This repository is official Tensorflow implementation of paper:

Our source code is based on an open deep learning compiler stack Apache TVM (https://github.com/apache/tvm) and Microsoft nni (https://github.com/microsoft/nni).

PocketFlow is an integrated toolkit for deep learning model compression, distributed training, and mobile format optimization. It provides a system for reducing the size and complexity of neural networks to improve inference efficiency, featuring a dedicated engine for knowledge distillation and a mobile model optimizer. The framework differentiates itself through an automated hyperparameter tuning system that uses reinforcement learning and statistical models to determine optimal compression ratios and layer-wise bit allocation. It also includes a distributed training system that utilizes mu

This repository contains Pytorch implementation of experiments from the paper Fast Lossless Neural Compression with Integer-Only Discrete Flows. The implementation is based on Integer Discrete Flows. rANS entropy coding in C language is based on local bits back.