Use the NGC CLI to download:
Copied!
Resource
U-Net allows for seamless segmentation of 2D images, with high accuracy and performance.
Use the NGC CLI to download:
Copied!
Changelog
June 2020
- Updated training and inference accuracy with A100 results
- Updated training and inference performance with A100 results
February 2020
- Updated README template
- Added cross-validation for accuracy measurements
- Changed optimizer to Adam and updated accuracy table
- Updated performance values
July 2019
- Added inference benchmark for T4
- Added inference example scripts
- Added inference benchmark measuring latency
- Added TRT/TF-TRT support
- Updated Pre-trained model on NGC registry
June 2019
- Updated README template
April 2019
- Initial release
Known issues
There are no known issues in this release.