rishizek/tensorflow-deeplab-v3-plus
TensorFlow implementation of DeepLabv3+ for semantic image segmentation on PASCAL VOC and Cityscapes datasets.
Not currently ranked — collecting fresh signals.
star history
This repository reproduces the DeepLabv3+ semantic image segmentation model in TensorFlow. It implements an encoder-decoder architecture with atrous separable convolutions for pixel-level image segmentation. The project provides training scripts and utilities for working with standard computer vision datasets including PASCAL VOC and Cityscapes, handling data preparation in TFRecord format.
Frequently asked
- What is rishizek/tensorflow-deeplab-v3-plus?
- TensorFlow implementation of DeepLabv3+ for semantic image segmentation on PASCAL VOC and Cityscapes datasets.
- Is tensorflow-deeplab-v3-plus open source?
- Yes — rishizek/tensorflow-deeplab-v3-plus is open source, released under the MIT license.
- What language is tensorflow-deeplab-v3-plus written in?
- rishizek/tensorflow-deeplab-v3-plus is primarily written in Python.
- How popular is tensorflow-deeplab-v3-plus?
- rishizek/tensorflow-deeplab-v3-plus has 840 stars on GitHub.
- Where can I find tensorflow-deeplab-v3-plus?
- rishizek/tensorflow-deeplab-v3-plus is on GitHub at https://github.com/rishizek/tensorflow-deeplab-v3-plus.