carlsummer/python_developer_tools
论文复现，多机多卡
This toolkit helps AI/ML practitioners and researchers quickly reproduce academic papers and implement deep learning models, especially in computer vision. It provides pre-built components like common neural network layers, attention mechanisms, loss functions, optimizers, and training utilities for tasks like image classification and object detection. You input raw image datasets and model architectures, and it helps you get trained models and research results.
No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer working on computer vision tasks and need a collection of readily available, optimized building blocks to accelerate model development, replicate research papers, or conduct experiments with different deep learning components.
Not ideal if you are looking for a high-level, opinionated framework for general machine learning tasks or if you need robust, production-ready APIs rather than modular research components.
Stars
49
Forks
10
Language
HTML
License
Apache-2.0
Category
Last pushed
Apr 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/carlsummer/python_developer_tools"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
PaddlePaddle/models
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models...