Functions, losses, and module blocks to share between experiments.
Project description
Pugh Torch
Functions, losses, and module blocks to share between experiments.
Features
- Additional methods to TensorBoard summary writer for adding normalized images and semantic segmentation images.
- hetero_cross_entropy for cross_entropy loss across heterogeneous datasets
Installation
Stable Release: pip install pugh_torch
Development Head: pip install git+https://github.com/BrianPugh/pugh_torch.git
Documentation
For full package documentation please visit BrianPugh.github.io/pugh_torch.
Free software: MIT license
Changelog
All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
[0.3.0] - 2020-09-21
Added
- Text label adding to TensorBoard Images
- ResizeShortest augmentation transform
- Unit Testing utilities
- basic Datasets API
- A bunch of useful dependencies added.
[0.2.0] - 2020-09-15
Added
- Additional extra_requires in preparation for docker release.
[0.1.0] - 2020-09-13
Added
- Initial Release
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pugh_torch-0.3.0.tar.gz
(23.9 kB
view hashes)
Built Distribution
Close
Hashes for pugh_torch-0.3.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3f754c0e7fbe0fa245783806acb6ad76060b05df3b9801b69d9a16f6cb2cdd3b |
|
MD5 | 4efa8442129cf88ddaceed2e1f8e4494 |
|
BLAKE2b-256 | 0522c6f09dad2e5b63952ce87e7edb19c1d06f8dc409c73e7626c9e9c66bde82 |