A memory-efficient implementation of DenseNets

Overview

efficient_densenet_pytorch

A PyTorch >=1.0 implementation of DenseNets, optimized to save GPU memory.

Recent updates

  1. Now works on PyTorch 1.0! It uses the checkpointing feature, which makes this code WAY more efficient!!!

Motivation

While DenseNets are fairly easy to implement in deep learning frameworks, most implmementations (such as the original) tend to be memory-hungry. In particular, the number of intermediate feature maps generated by batch normalization and concatenation operations grows quadratically with network depth. It is worth emphasizing that this is not a property inherent to DenseNets, but rather to the implementation.

This implementation uses a new strategy to reduce the memory consumption of DenseNets. We use checkpointing to compute the Batch Norm and concatenation feature maps. These intermediate feature maps are discarded during the forward pass and recomputed for the backward pass. This adds 15-20% of time overhead for training, but reduces feature map consumption from quadratic to linear.

This implementation is inspired by this technical report, which outlines a strategy for efficient DenseNets via memory sharing.

Requirements

  • PyTorch >=1.0.0
  • CUDA

Usage

In your existing project: There is one file in the models folder.

If you care about speed, and memory is not an option, pass the efficient=False argument into the DenseNet constructor. Otherwise, pass in efficient=True.

Options:

  • All options are described in the docstrings of the model files
  • The depth is controlled by block_config option
  • efficient=True uses the memory-efficient version
  • If you want to use the model for ImageNet, set small_inputs=False. For CIFAR or SVHN, set small_inputs=True.

Running the demo:

The only extra package you need to install is python-fire:

pip install fire
  • Single GPU:
CUDA_VISIBLE_DEVICES=0 python demo.py --efficient True --data <path_to_folder_with_cifar10> --save <path_to_save_dir>
  • Multiple GPU:
CUDA_VISIBLE_DEVICES=0,1,2 python demo.py --efficient True --data <path_to_folder_with_cifar10> --save <path_to_save_dir>

Options:

  • --depth (int) - depth of the network (number of convolution layers) (default 40)
  • --growth_rate (int) - number of features added per DenseNet layer (default 12)
  • --n_epochs (int) - number of epochs for training (default 300)
  • --batch_size (int) - size of minibatch (default 256)
  • --seed (int) - manually set the random seed (default None)

Performance

A comparison of the two implementations (each is a DenseNet-BC with 100 layers, batch size 64, tested on a NVIDIA Pascal Titan-X):

Implementation Memory cosumption (GB/GPU) Speed (sec/mini batch)
Naive 2.863 0.165
Efficient 1.605 0.207
Efficient (multi-GPU) 0.985 -

Other efficient implementations

Reference

@article{pleiss2017memory,
  title={Memory-Efficient Implementation of DenseNets},
  author={Pleiss, Geoff and Chen, Danlu and Huang, Gao and Li, Tongcheng and van der Maaten, Laurens and Weinberger, Kilian Q},
  journal={arXiv preprint arXiv:1707.06990},
  year={2017}
}
Owner
Geoff Pleiss
Geoff Pleiss
A Dataset for Direct Quotation Extraction and Attribution in News Articles.

DirectQuote - A Dataset for Direct Quotation Extraction and Attribution in News Articles DirectQuote is a corpus containing 19,760 paragraphs and 10,3

THUNLP-MT 9 Sep 23, 2022
DexterRedTool - Dexter's Red Team Tool that creates cronjob/task scheduler to consistently creates users

DexterRedTool Author: Dexter Delandro CSEC 473 - Spring 2022 This tool persisten

2 Feb 16, 2022
Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation)

Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation) Download Synthia dataset The model uses

32 Sep 21, 2022
Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

UniSpeech The family of UniSpeech: UniSpeech (ICML 2021): Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR UniSpeech-

Microsoft 282 Jan 09, 2023
Build a small, 3 domain internet using Github pages and Wikipedia and construct a crawler to crawl, render, and index.

TechSEO Crawler Build a small, 3 domain internet using Github pages and Wikipedia and construct a crawler to crawl, render, and index. Play with the r

JR Oakes 57 Nov 24, 2022
Magisk module to enable hidden features on Android 12 Developer Preview 1.

Android 12 Extensions This is a Magisk module that enables hidden features on Android 12 Developer Preview 1. Features Scrolling screenshots Wallpaper

Danny Lin 384 Jan 06, 2023
Code for the paper "SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness" (NeurIPS 2021)

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness (NeurIPS2021) This repository contains code for the paper "Smo

Jongheon Jeong 17 Dec 27, 2022
Do Smart Glasses Dream of Sentimental Visions? Deep Emotionship Analysis for Eyewear Devices

EMOShip This repository contains the EMO-Film dataset described in the paper "Do Smart Glasses Dream of Sentimental Visions? Deep Emotionship Analysis

1 Nov 18, 2022
Image classification for projects and researches

This is a tool to help you quickly solve classification problems including: data analysis, training, report results and model explanation.

Nguyễn Trường Lâu 2 Dec 27, 2021
PyTorch implementation of residual gated graph ConvNets, ICLR’18

Residual Gated Graph ConvNets April 24, 2018 Xavier Bresson http://www.ntu.edu.sg/home/xbresson https://github.com/xbresson https://twitter.com/xbress

Xavier Bresson 112 Aug 10, 2022
Embodied Intelligence via Learning and Evolution

Embodied Intelligence via Learning and Evolution This is the code for the paper Embodied Intelligence via Learning and Evolution Agrim Gupta, Silvio S

Agrim Gupta 111 Dec 13, 2022
A simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

this is a simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

crispengari 5 Dec 09, 2021
Most popular metrics used to evaluate object detection algorithms.

Most popular metrics used to evaluate object detection algorithms.

Rafael Padilla 4.4k Dec 25, 2022
AI-UPV at IberLEF-2021 EXIST task: Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models

AI-UPV at IberLEF-2021 EXIST task: Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models Descrip

Angel de Paula 1 Jun 08, 2022
Uncertain natural language inference

Uncertain Natural Language Inference This repository hosts the code for the following paper: Tongfei Chen*, Zhengping Jiang*, Adam Poliak, Keisuke Sak

Tongfei Chen 14 Sep 01, 2022
Bravia core script for python

Bravia-Core-Script You need to have a mandatory account If this L3 does not work, try another L3. enjoy

5 Dec 26, 2021
A Unified Framework and Analysis for Structured Knowledge Grounding

UnifiedSKG 📚 : Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models Code for paper UnifiedSKG: Unifying and Mu

HKU NLP Group 370 Dec 21, 2022
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech Jaehyeon Kim, Jungil Kong, and Juhee Son In our rece

Jaehyeon Kim 1.7k Jan 08, 2023
Official code for the CVPR 2021 paper "How Well Do Self-Supervised Models Transfer?"

How Well Do Self-Supervised Models Transfer? This repository hosts the code for the experiments in the CVPR 2021 paper How Well Do Self-Supervised Mod

Linus Ericsson 157 Dec 16, 2022
Convert BART models to ONNX with quantization. 3X reduction in size, and upto 3X boost in inference speed

fast-Bart Reduction of BART model size by 3X, and boost in inference speed up to 3X BART implementation of the fastT5 library (https://github.com/Ki6a

Siddharth Sharma 19 Dec 09, 2022