HasnainRaz/FC-DenseNet-TensorFlow

Fully Convolutional DenseNet (A.K.A 100 layer tiramisu) for semantic segmentation of images implemented in TensorFlow.

47
/ 100
Emerging

This project offers a clear and modular implementation of the Fully Convolutional DenseNet, known as '100 layer tiramisu,' for semantic image segmentation. It takes an image as input and outputs a pixel-wise classification, effectively assigning each pixel to a specific category. This tool is primarily for machine learning researchers and practitioners who want to understand and experiment with this specific neural network architecture.

124 stars. No commits in the last 6 months.

Use this if you are a deep learning researcher or practitioner looking for a highly readable and modular TensorFlow implementation of the FC-DenseNet for semantic image segmentation.

Not ideal if you are looking for a pre-trained, ready-to-use model for image segmentation without needing to understand or modify the underlying network architecture.

semantic-segmentation deep-learning-research image-analysis neural-network-architecture computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

124

Forks

41

Language

Python

License

MIT

Last pushed

Dec 21, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HasnainRaz/FC-DenseNet-TensorFlow"

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