hlt-mt/pangolinn
As a Pangolin looks for bugs and catches them, the goal of this library is ot help developers finding bugs in their neural networks and newly-created models.
This library helps machine learning engineers and researchers ensure their neural network models work correctly before deployment. It takes a newly developed neural network model and a set of predefined tests, then checks if the model behaves as expected under various conditions, such as handling padded input or maintaining causality. The output is a report detailing whether the model passed or failed these crucial checks, helping developers catch bugs early.
No commits in the last 6 months. Available on PyPI.
Use this if you are developing new neural network architectures and need to systematically verify their fundamental properties like padding invariance or causal behavior.
Not ideal if you are a non-developer seeking an automated solution for general machine learning model validation or performance benchmarking.
Stars
13
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
May 18, 2024
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hlt-mt/pangolinn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
emlearn/emlearn
Machine Learning inference engine for Microcontrollers and Embedded devices
analogdevicesinc/ai8x-training
Model Training for ADI's MAX78000 and MAX78002 Edge AI Devices
DT42/BerryNet
Deep learning gateway on Raspberry Pi and other edge devices
SummerGift/EmbeddedSystem
:books: 计算机体系架构、嵌入式系统基础与主流编程语言相关内容总结
eclypse-org/eclypse
An Edge-Cloud python platform for simulated (and emulated) runtime environments