PyTorch implementation of SimSiam: Exploring Simple Siamese Representation Learning

Related tags

Deep Learningsimsiam
Overview

SimSiam: Exploring Simple Siamese Representation Learning

simsiam

This is a PyTorch implementation of the SimSiam paper:

@Article{chen2020simsiam,
  author  = {Xinlei Chen and Kaiming He},
  title   = {Exploring Simple Siamese Representation Learning},
  journal = {arXiv preprint arXiv:2011.10566},
  year    = {2020},
}

Preparation

Install PyTorch and download the ImageNet dataset following the official PyTorch ImageNet training code. Similar to MoCo, the code release contains minimal modifications for both unsupervised pre-training and linear classification to that code.

In addition, install apex for the LARS implementation needed for linear classification.

Unsupervised Pre-Training

Only multi-gpu, DistributedDataParallel training is supported; single-gpu or DataParallel training is not supported.

To do unsupervised pre-training of a ResNet-50 model on ImageNet in an 8-gpu machine, run:

python main_simsiam.py \
  -a resnet50 \
  --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 \
  --fix-pred-lr \
  [your imagenet-folder with train and val folders]

The script uses all the default hyper-parameters as described in the paper, and uses the default augmentation recipe from MoCo v2.

The above command performs pre-training with a non-decaying predictor learning rate for 100 epochs, corresponding to the last row of Table 1 in the paper.

Linear Classification

With a pre-trained model, to train a supervised linear classifier on frozen features/weights in an 8-gpu machine, run:

python main_lincls.py \
  -a resnet50 \
  --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 \
  --pretrained [your checkpoint path]/checkpoint_0099.pth.tar \
  --lars \
  [your imagenet-folder with train and val folders]

The above command uses LARS optimizer and a default batch size of 4096.

Models and Logs

Our pre-trained ResNet-50 models and logs:

pre-train
epochs
batch
size
pre-train
ckpt
pre-train
log
linear cls.
ckpt
linear cls.
log
top-1 acc.
100 512 link link link link 68.1
100 256 link link link link 68.3

Settings for the above: 8 NVIDIA V100 GPUs, CUDA 10.1/CuDNN 7.6.5, PyTorch 1.7.0.

Transferring to Object Detection

Same as MoCo for object detection transfer, please see moco/detection.

License

This project is under the CC-BY-NC 4.0 license. See LICENSE for details.

Owner
Facebook Research
Facebook Research
NovelD: A Simple yet Effective Exploration Criterion

NovelD: A Simple yet Effective Exploration Criterion Intro This is an implementation of the method proposed in NovelD: A Simple yet Effective Explorat

29 Dec 05, 2022
Fast image augmentation library and an easy-to-use wrapper around other libraries

Albumentations Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to inc

11.4k Jan 09, 2023
Hippocampal segmentation using the UNet network for each axis

Hipposeg Hippocampal segmentation using the UNet network for each axis, inspired by https://github.com/MICLab-Unicamp/e2dhipseg Red: False Positive Gr

Juan Carlos Aguirre Arango 0 Sep 02, 2021
Pytorch Implementation for NeurIPS (oral) paper: Pixel Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation

Pixel-Level Cycle Association This is the Pytorch implementation of our NeurIPS 2020 Oral paper Pixel-Level Cycle Association: A New Perspective for D

87 Oct 19, 2022
This repository implements and evaluates convolutional networks on the Möbius strip as toy model instantiations of Coordinate Independent Convolutional Networks.

Orientation independent Möbius CNNs This repository implements and evaluates convolutional networks on the Möbius strip as toy model instantiations of

Maurice Weiler 59 Dec 09, 2022
Rest API Written In Python To Classify NSFW Images.

Rest API Written In Python To Classify NSFW Images.

Wahyusaputra 2 Dec 23, 2021
This library is a location of the LegacyLogger for PyTorch Lightning.

neptune-contrib Documentation See neptune-contrib documentation site Installation Get prerequisites python versions 3.5.6/3.6 are supported Install li

neptune.ai 26 Oct 07, 2021
YOLOv5🚀 reproduction by Guo Quanhao using PaddlePaddle

YOLOv5-Paddle YOLOv5 🚀 reproduction by Guo Quanhao using PaddlePaddle 支持AutoBatch 支持AutoAnchor 支持GPU Memory 快速开始 使用AIStudio高性能环境快速构建YOLOv5训练(PaddlePa

QuanHao Guo 20 Nov 14, 2022
SciPy fixes and extensions

scipyx SciPy is large library used everywhere in scientific computing. That's why breaking backwards-compatibility comes as a significant cost and is

Nico Schlömer 16 Jul 17, 2022
A real-time motion capture system that estimates poses and global translations using only 6 inertial measurement units

TransPose Code for our SIGGRAPH 2021 paper "TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors". This repository

Xinyu Yi 261 Dec 31, 2022
Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

PSML paper: Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors PSML_IONE,PSML_ABNE,PSML_DEEPLINK,PSML_SNNA: numpy

13 Nov 27, 2022
An example of semantic segmentation using tensorflow in eager execution.

Semantic segmentation using Tensorflow eager execution Requirement Python 2.7+ Tensorflow-gpu OpenCv H5py Scikit-learn Numpy Imgaug Train with eager e

Iñigo Alonso Ruiz 25 Sep 29, 2022
MATLAB codes of the book "Digital Image Processing Fourth Edition" converted to Python

Digital Image Processing Python MATLAB codes of the book "Digital Image Processing Fourth Edition" converted to Python TO-DO: Refactor scripts, curren

Merve Noyan 24 Oct 16, 2022
modelvshuman is a Python library to benchmark the gap between human and machine vision

modelvshuman is a Python library to benchmark the gap between human and machine vision. Using this library, both PyTorch and TensorFlow models can be evaluated on 17 out-of-distribution datasets with

Bethge Lab 244 Jan 03, 2023
Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

Readme File for "Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis" by Ham, Imai, and Janson. (2022) All scripts were written and

0 Jan 27, 2022
Logistic Bandit experiments. Official code for the paper "Jointly Efficient and Optimal Algorithms for Logistic Bandits".

Code for the paper Jointly Efficient and Optimal Algorithms for Logistic Bandits, by Louis Faury, Marc Abeille, Clément Calauzènes and Kwang-Sun Jun.

Faury Louis 1 Jan 22, 2022
A general-purpose encoder-decoder framework for Tensorflow

READ THE DOCUMENTATION CONTRIBUTING A general-purpose encoder-decoder framework for Tensorflow that can be used for Machine Translation, Text Summariz

Google 5.5k Jan 07, 2023
C3d-pytorch - Pytorch porting of C3D network, with Sports1M weights

C3D for pytorch This is a pytorch porting of the network presented in the paper Learning Spatiotemporal Features with 3D Convolutional Networks How to

Davide Abati 311 Jan 06, 2023
code for EMNLP 2019 paper Text Summarization with Pretrained Encoders

PreSumm This code is for EMNLP 2019 paper Text Summarization with Pretrained Encoders Updates Jan 22 2020: Now you can Summarize Raw Text Input!. Swit

Yang Liu 1.2k Dec 28, 2022
OpenLT: An open-source project for long-tail classification

OpenLT: An open-source project for long-tail classification Supported Methods for Long-tailed Recognition: Cross-Entropy Loss Focal Loss (ICCV'17) Cla

Ming Li 37 Sep 15, 2022