imbalanced-regression
pneumonia_detection
Our great sponsors
imbalanced-regression | pneumonia_detection | |
---|---|---|
1 | 2 | |
757 | 13 | |
- | - | |
1.8 | 0.0 | |
about 2 years ago | almost 2 years ago | |
Python | Python | |
MIT License | MIT License |
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.
imbalanced-regression
-
[R] Strategies and Tactics for Regression on Imbalanced Data
Code (+ dataset + models): https://github.com/YyzHarry/imbalanced-regression
pneumonia_detection
-
Help with resume! Just graduated (:
Same goes for your pneumonia project. Not a hiring manager although if I got asked by my lead to rate an application, I'd say projects you copy from Google are a big minus and if I find an applicants project on google within a minute, I'd have a lot less confidence in said candidate vs. somebody who is out there producing original projects. 1 really good original project is better and more valuable than 2 or 3 projects from tutorials.
-
I wanted to try streamlit, so I trained a model to diagnose lung X-Rays (Pneumonia) and visualised it with streamlit [not hosted]
The model had a ~91% accuracy on a 300 image test set. It had the most problems with false positives (which I guess is better then false negatives🤷‍♂️) --> check confusion matrix in github readme for more
What are some alternatives?
autogluon - AutoGluon: Fast and Accurate ML in 3 Lines of Code
streamlit - Streamlit — A faster way to build and share data apps.
d2l-en - Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
ludwig - Low-code framework for building custom LLMs, neural networks, and other AI models
healthsea - Healthsea is a spaCy pipeline for analyzing user reviews of supplementary products for their effects on health.
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
multi-domain-imbalance - [ECCV 2022] Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization, and Beyond