KevinMusgrave / Powerful Benchmarker
A PyTorch library for benchmarking deep metric learning. It's powerful.
Stars: ✭ 272
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Powerful Benchmarker
proxy-synthesis
Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)
Stars: ✭ 30 (-88.97%)
Mutual labels: metric-learning, image-retrieval
Batch Dropblock Network
Official source code of "Batch DropBlock Network for Person Re-identification and Beyond" (ICCV 2019)
Stars: ✭ 304 (+11.76%)
Mutual labels: image-retrieval, metric-learning
Pytorch Metric Learning
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
Stars: ✭ 3,936 (+1347.06%)
Mutual labels: image-retrieval, metric-learning
Revisiting deep metric learning pytorch
(ICML 2020) This repo contains code for our paper "Revisiting Training Strategies and Generalization Performance in Deep Metric Learning" (https://arxiv.org/abs/2002.08473) to facilitate consistent research in the field of Deep Metric Learning.
Stars: ✭ 172 (-36.76%)
Mutual labels: image-retrieval, metric-learning
Pytorch Image Retrieval
A PyTorch framework for an image retrieval task including implementation of N-pair Loss (NIPS 2016) and Angular Loss (ICCV 2017).
Stars: ✭ 203 (-25.37%)
Mutual labels: image-retrieval, metric-learning
symmetrical-synthesis
Official Tensorflow implementation of "Symmetrical Synthesis for Deep Metric Learning" (AAAI 2020)
Stars: ✭ 67 (-75.37%)
Mutual labels: metric-learning, image-retrieval
Hardnet
Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
Stars: ✭ 350 (+28.68%)
Mutual labels: image-retrieval, metric-learning
Person reid baseline pytorch
Pytorch ReID: A tiny, friendly, strong pytorch implement of object re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Stars: ✭ 2,963 (+989.34%)
Mutual labels: image-retrieval, metric-learning
GPQ
Generalized Product Quantization Network For Semi-supervised Image Retrieval - CVPR 2020
Stars: ✭ 60 (-77.94%)
Mutual labels: metric-learning, image-retrieval
disent
🧶 Modular VAE disentanglement framework for python built with PyTorch Lightning ▸ Including metrics and datasets ▸ With strongly supervised, weakly supervised and unsupervised methods ▸ Easily configured and run with Hydra config ▸ Inspired by disentanglement_lib
Stars: ✭ 41 (-84.93%)
Mutual labels: metric-learning
ycecream
Sweeter debugging and benchmarking Python programs.
Stars: ✭ 38 (-86.03%)
Mutual labels: benchmarking
Similarity-Adaptive-Deep-Hashing
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (TPAMI2018)
Stars: ✭ 18 (-93.38%)
Mutual labels: image-retrieval
LSQ
Linked SPARQL Queries (LSQ): Framework for RDFizing triple store (web) logs and performing SPARQL query extraction, analysis and benchmarking in order to produce datasets of Linked SPARQL Queries
Stars: ✭ 23 (-91.54%)
Mutual labels: benchmarking
profuzzbench
ProFuzzBench - A Benchmark for Stateful Protocol Fuzzing
Stars: ✭ 113 (-58.46%)
Mutual labels: benchmarking
ReBench
Execute and document benchmarks reproducibly.
Stars: ✭ 48 (-82.35%)
Mutual labels: benchmarking
diffusion-retrieval
Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations
Stars: ✭ 78 (-71.32%)
Mutual labels: image-retrieval
advrank
Adversarial Ranking Attack and Defense, ECCV, 2020.
Stars: ✭ 19 (-93.01%)
Mutual labels: metric-learning
ISeeNN
A CNN feature based image retrieval website
Stars: ✭ 15 (-94.49%)
Mutual labels: image-retrieval
Siamesenetwork Tensorflow
Using siamese network to do dimensionality reduction and similar image retrieval
Stars: ✭ 258 (-5.15%)
Mutual labels: image-retrieval
cbtool
Cloud Rapid Experimentation and Analysis Toolkit
Stars: ✭ 65 (-76.1%)
Mutual labels: benchmarking
Powerful Benchmarker
Documentation
Google Colab Examples
See the examples folder for notebooks that show a bit of this library's functionality.
A Metric Learning Reality Check
See supplementary material for the ECCV 2020 paper.
Benchmark results:
Benefits of this library
- Highly configurable:
- Yaml files for organized configuration
- A powerful command line syntax that allows you to merge, override, swap, apply, and delete config options.
- Customizable:
- Benchmark your own losses, miners, datasets etc. with a simple function call.
- Easy hyperparameter optimization:
- Append the ~BAYESIAN~ flag to the names of hyperparameters you want to optimize.
- Extensive logging:
- View experiment data in tensorboard, CSV and SQLite format.
- Reproducible:
- Config files are saved with each experiment and are easily reproduced.
- Trackable changes:
- Keep track of changes to an experiment's configuration.
Installation
pip install powerful-benchmarker
Citing the benchmark results or code
If you'd like to cite the benchmark results, please cite this paper:
@misc{musgrave2020metric,
title={A Metric Learning Reality Check},
author={Kevin Musgrave and Serge Belongie and Ser-Nam Lim},
year={2020},
eprint={2003.08505},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
Acknowledgements
Thank you to Ser-Nam Lim at Facebook AI, and my research advisor, Professor Serge Belongie. This project began during my internship at Facebook AI where I received valuable feedback from Ser-Nam, and his team of computer vision and machine learning engineers and research scientists.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].