Skip to content

Multimodal Deep Learning architectures that are more robust to noisy and adversarial data.

Notifications You must be signed in to change notification settings

ACFHarbinger/rgmc

Repository files navigation

Robust Geometric Multimodal Contrastive Learning Framework

Multimodal Deep Learning architectures that are robust to noisy and adversarial data.

Tech Stack

Adapted Code

This project contains code that was adapted from the following repositories:

Setup Conda Environment

To setup the conda environment for the project, you just need to run the following commands in the main directory:

conda env create -f environment.yml
conda activate RGMC

Setup Project

In order to setup the project, just run the python script to download and prepare all datasets:

python download_datasets.py

Running experiments

There are two different ways you can train and/or test models.

Command Line

In order to begin a new experiment from the command line, you must choose the architecture, dataset and stage for the experiment:

python main.py exp --a <architecture> --d <dataset> --s <train_model||train_classifier||test_model||test_classifier>

This will begin an experiment with the default hyper-parameters for the given architecture, dataset and stage, but you can also define the values you want for each hyper-parameter in the arguments (e.g., learning rate, batch size, number of epochs). For the full list of hyper-parameters you can tune, see.

Config File

You can also run several experiments in succession by reading a JSON file with a list of experimental configurations:

python main.py config --load_config <json_filepath>

If instead you want to run multiple experiments with all possible hyper-parameter permutations, you can load the configurations json file with the --config_permute <json_filepath> option.

Compare Experimental Results

For example, to compare metrics for a DAE-based classifier on the MHD dataset given different standard deviation values for gaussian noise on the image modality, you just need to run the following command:

python main.py compare -a dae -d mhd -s test_classifier --pc noise_std --pp target_modality

About

Multimodal Deep Learning architectures that are more robust to noisy and adversarial data.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages