FastestDet
autogluon
| FastestDet | autogluon | |
|---|---|---|
| 1 | 8 | |
| 713 | 7,201 | |
| - | 2.7% | |
| 0.0 | 9.6 | |
| about 1 year ago | 3 days ago | |
| Python | Python | |
| BSD 3-clause "New" or "Revised" License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
FastestDet
-
FastestDet: a new ultra real-time anchor free target detection algorithm designed for ARM CPU, with only 250K parameters,
The time consumption in the table is measured by ncnn. The test platform is RK3568 ARM CPU. Compared with Yolo-fastest, the time consumption of fastestdet single core is reduced by 50%, and the index of map0.5 is 3.4% higher than Yolo-fastest. In fact, due to the increase of input resolution, the calculation amount of FastestDet is nearly twice that of Yolo-fastest. However, thanks to the minimalist network structure and the reduction of memory access, the actual test time on multiple platforms is greatly reduced, especially on single core or weak performance platforms, and the speed is increased by 50%+
autogluon
-
pip install remyxai - easiest way to create custom vision models
This seems not very convincing. There are other popular frameworks that provide AutoML with existing datasets (eg https://github.com/autogluon/autogluon)
- autogluon: NEW Data - star count:5070.0
-
[D] Where is AutoML for NNs?
https://github.com/awslabs/autogluon works well for image/text/tabular data
- k-fold bagging in Autogluon - Tabular
-
What will the data science job market be like in 5 years?
Some AutoML is getting pretty good, AutoGluon is very solid for tabular data. That being said you still need to have your data in tabular format and deployment still requires some effort.
What are some alternatives?
PaddleViT - :robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
FLAML - A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
layout-parser - A Unified Toolkit for Deep Learning Based Document Image Analysis
autokeras - AutoML library for deep learning
ssd_keras - A Keras port of Single Shot MultiBox Detector
auto-sklearn - Automated Machine Learning with scikit-learn
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
imbalanced-regression - [ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
tabnet - PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf
automlbenchmark - OpenML AutoML Benchmarking Framework
pytorch-metric-learning - The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
shapley - The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).