TimDettmers / sparse_learning
Sparse learning library and sparse momentum resources.
☆377Updated 2 years ago
Related projects: ⓘ
- PyTorch library to facilitate development and standardized evaluation of neural network pruning methods.☆420Updated last year
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆315Updated last year
- PyTorch layer-by-layer model profiler☆608Updated 3 years ago
- Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours☆396Updated 3 years ago
- A large scale study of Knowledge Distillation.☆217Updated 4 years ago
- ☆215Updated last month
- Papers for deep neural network compression and acceleration☆394Updated 3 years ago
- A repository in preparation for open-sourcing lottery ticket hypothesis code.☆625Updated 2 years ago
- Naszilla is a Python library for neural architecture search (NAS)☆303Updated last year
- PyTorch Implementation of DARTS: Differentiable Architecture Search☆438Updated 2 years ago
- Library for faster pinned CPU <-> GPU transfer in Pytorch☆682Updated 4 years ago
- Code for Neural Architecture Search without Training (ICML 2021)☆454Updated 3 years ago
- Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)☆1,506Updated 4 years ago
- Implements quantized distillation. Code for our paper "Model compression via distillation and quantization"☆329Updated last month
- ConvNet training using pytorch☆345Updated 3 years ago
- Fast Block Sparse Matrices for Pytorch☆546Updated 3 years ago
- Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019☆905Updated last year
- Implementations of ideas from recent papers☆391Updated 3 years ago
- NASBench: A Neural Architecture Search Dataset and Benchmark☆679Updated last year
- Code release for paper "Random Search and Reproducibility for NAS"☆167Updated 5 years ago
- Learning Sparse Neural Networks through L0 regularization☆236Updated 4 years ago
- PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference☆873Updated 5 years ago
- A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.☆706Updated 4 years ago
- Summary, Code for Deep Neural Network Quantization☆525Updated 2 months ago
- NAS-Bench-201 API and Instruction☆625Updated 3 years ago
- Collection of recent methods on (deep) neural network compression and acceleration.☆922Updated 2 weeks ago
- ☆142Updated last year
- A Re-implementation of Fixed-update Initialization☆150Updated 5 years ago
- ☆531Updated 2 years ago
- Pruning Neural Networks with Taylor criterion in Pytorch☆310Updated 4 years ago