Skip to content

Official implementation of bachelor thesis "Convolutional Neural Networks with Local Context Masks" with updated code. For access to original framework, contact the author.

Notifications You must be signed in to change notification settings

paplhjak/Contextus

Repository files navigation

Convolutional Neural Networks with Local Context Masks

This repository is the official implementation of [Convolutional Neural Networks with Local Context Masks].

Environment

PyTorch 1.5.0

Python 3.7.2

CUDA 10.0.130

For comparison with Pixel-Adaptive Convolution, pacnet must be cloned inside the repository.

Training

The training framework is implemented for use within RCI cluster data storage. User must first edit data_loader/data_loaders.py and configuration files to begin training elsewhere.

To train the models using method described in the thesis, run this command:

python train.py -c <path_to_config> -r <path_to_model_checkpoint>

About

Official implementation of bachelor thesis "Convolutional Neural Networks with Local Context Masks" with updated code. For access to original framework, contact the author.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages