pylocron 0.1.2

Modules, operations and models for computer vision in PyTorch

Holocron

Implementations of recent Deep Learning tricks in Computer Vision, easily paired up with your favorite framework and model zoo.

Holocrons were information-storage datacron devices used by both the Jedi Order and the Sith that contained ancient lessons or valuable information in holographic form.

Source: Wookieepedia

Table of Contents

• Getting Started
  • Prerequisites
  • Installation
• Usage
• Technical Roadmap
• Documentation
• Contributing
• License

Note: support of activation mapper and model summary has been dropped and outsourced to independent packages (torch-cam & torch-scan) to clarify project scope.

Getting started

Prerequisites

• Python 3.6 (or more recent)
• pip

Installation

You can install the package using pypi as follows:

pip install pylocron

or using conda:

conda install -c frgfm pylocron

Usage

nn

Main features

• Activation: SiLU/Swish, Mish, NLReLU
• Loss: Focal Loss, MultiLabelCrossEntropy, LabelSmoothingCrossEntropy, MixupLoss
• Convolutions: NormConv2d, Add2d, SlimConv2d
• Regularization: DropBlock

models

Main features

• Classification: Res2Net (based on the great implementation from gasvn), darknet24, darknet19, darknet53, ResNet, ResNeXt, ReXNet.
• Detection: YOLOv1, YOLOv2
• Segmentation: U-Net, UNet++, UNet3+

ops

Main features

• boxes: Distance-IoU & Complete-IoU losses

optim

Main features

• Optimizer: LARS, Lamb, RAdam, TAdam and customized versions (RaLars)
• Optimizer wrapper: Lookahead, Scout (experimental)
• Scheduler: OneCycleScheduler

Usage

You can use the OneCycleScheduler just like any other LR scheduler of pytorch. Please note that it is designed to take step at every iteration. Over the full training, the learning rate should look like:

Here two different parameter groups have been made to illustrate the effect of the scheduler. This implementation was made before PyTorch officially had an implementation. For better support, it is recommended to consider the PyTorch version.

Technical roadmap

The project is currently under development, here are the objectives for the next releases:

• Standardize models: standardize models by task.
• Speed benchmark: compare holocron.nn functions execution speed.
• Reference scripts: add reference training scripts

Documentation

The full package documentation is available here for detailed specifications. The documentation was built with Sphinx using a theme provided by Read the Docs

Contributing

Please refer to CONTRIBUTING if you wish to contribute to this project.

License

Distributed under the MIT License. See LICENSE for more information.