Official Code for "Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning"

Last update: Nov 25, 2022

Related tags

Deep Learning CMSF

Overview

CMSF

Official Code for "Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning"

Requirements

Python >= 3.7.6
PyTorch >= 1.4
torchvision >= 0.5.0
faiss-gpu >= 1.6.1

Install PyTorch and ImageNet dataset following the official PyTorch ImageNet training code. We used Python 3.7 for our experiments.

Install PyTorch (pytorch.org)

To run NN and CMSF-KM, you require to install FAISS.

FAISS:

Install FAISS (https://github.com/facebookresearch/faiss/blob/master/INSTALL.md)

Training Self-Supservised CMSF-KM

python self_supervised/train_msf_km.py \
  --cos \
  --weak_strong \
  --learning_rate 0.05 \
  --epochs 200 \
  --arch resnet50 \
  --topk 5 \
  --momentum 0.99 \
  --mem_bank_size 128000 \
  --num_clusters 50000 \
  --checkpoint_path <CHECKPOINT PATH> \
  <DATASET PATH>

Training Self-Supservised CMSF-2Q

python self_supervised/train_msf_2q.py \
  --cos \
  --weak_strong \
  --learning_rate 0.05 \
  --epochs 200 \
  --arch resnet50 \
  --topk 5 \
  --momentum 0.99 \
  --mem_bank_size 128000 \
  --topkp 5 \
  --checkpoint_path <CHECKPOINT PATH> \
  <DATASET PATH>

Training Supservised

Following command can be used to train the CMSF(Supervised Learning)

python supervised/train_sup_msf.py \
  --cos \
  --weak_strong \
  --learning_rate 0.05 \
  --epochs 200 \
  --arch resnet50 \
  --topk 10 \
  --momentum 0.99 \
  --mem_bank_size 128000 \
  --checkpoint_path <CHECKPOINT PATH> \
  <DATASET PATH>

License

This project is under the MIT license.

Official Code for "Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning"

Related tags

Overview

CMSF

Requirements

Training Self-Supservised CMSF-KM

Training Self-Supservised CMSF-2Q

Training Supservised

License

Owner

Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond

Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

Perspective: Julia for Biologists

AI Flow is an open source framework that bridges big data and artificial intelligence.

Feature board for ERPNext

Simple PyTorch implementations of Badnets on MNIST and CIFAR10.

Easy to use Python camera interface for NVIDIA Jetson

Title: Graduate-Admissions-Predictor

Implementation of Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis

Discriminative Condition-Aware PLDA

Only works with the dashboard version / branch of jesse

Hunt down social media accounts by username across social networks

Repo for Photon-Starved Scene Inference using Single Photon Cameras, ICCV 2021

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

A PyTorch version of You Only Look at One-level Feature object detector

Dogs classification with Deep Metric Learning using some popular losses

Model Serving Made Easy

"Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion"(WWW 2021)

The official code of "SCROLLS: Standardized CompaRison Over Long Language Sequences".

Do you like Quick, Draw? Well what if you could train/predict doodles drawn inside Streamlit? Also draws lines, circles and boxes over background images for annotation.