Sakib1263/TF-1D-2D-ResNetV1-2-SEResNet-ResNeXt-SEResNeXt

Models supported: ResNet, ResNetV2, SE-ResNet, ResNeXt, SE-ResNeXt [layers: 18, 34, 50, 101, 152] (1D and 2D versions with DEMO for Classification and Regression).

41
/ 100
Emerging

This project offers pre-built deep learning models for classifying or predicting outcomes from both one-dimensional data, like sensor readings or time series, and two-dimensional data, such as images. It takes raw data, processes it through advanced neural network architectures (ResNet, ResNeXt), and outputs classifications (e.g., 'cat' or 'dog') or numerical predictions. This is ideal for machine learning engineers or researchers who need to quickly implement powerful, battle-tested models for their predictive tasks.

No commits in the last 6 months.

Use this if you need to apply robust deep learning models for classification or regression on either 1D sequence data or 2D image-like data, and want highly configurable, production-ready architectures.

Not ideal if you're looking for a low-code solution for general data analysis, or if your problem doesn't involve deep learning on structured 1D or 2D inputs.

deep-learning image-classification time-series-analysis predictive-modeling pattern-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

44

Forks

9

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Sakib1263/TF-1D-2D-ResNetV1-2-SEResNet-ResNeXt-SEResNeXt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.