hellochick/ICNet-tensorflow
A TensorFlow implementation of the ICNet model for real-time semantic segmentation on high-resolution images.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow implementation of the ICNet paper for semantic segmentation, which generates a segmentation mask for every pixel in an image. The model is based on ResNet50 with three branches and auxiliary paths for multi-scale feature extraction. It includes pre-trained weights for Cityscapes and ADE20K datasets, along with training and inference code. Weights were converted from the original caffe implementation.
Frequently asked
- What is hellochick/ICNet-tensorflow?
- A TensorFlow implementation of the ICNet model for real-time semantic segmentation on high-resolution images.
- Is ICNet-tensorflow open source?
- Yes — hellochick/ICNet-tensorflow is an open-source project tracked on heatdrop.
- What language is ICNet-tensorflow written in?
- hellochick/ICNet-tensorflow is primarily written in Jupyter Notebook.
- How popular is ICNet-tensorflow?
- hellochick/ICNet-tensorflow has 404 stars on GitHub.
- Where can I find ICNet-tensorflow?
- hellochick/ICNet-tensorflow is on GitHub at https://github.com/hellochick/ICNet-tensorflow.