This repository is the official implementation of all the models mentioned in the Radio Map Estimation with Deep Dual Path Autoencoders and Skip Connection Learning paper.

• data_utils.py contains all the data-related utilities. Specifically, it defines the pytorch implementation of the radiomap dataset and the data scaler used in the paper.
• models contains all the models mentioned in the paper. The autoencoder.py file contains an abstract autoencoder class implementation. The classes in autoencoders.py inherit the hyperparameters and methods of the autoencoder class to define all the architectures of the paper. The rest of the files correspond to specific autoencoder arhitectures and contain implementations of encoders and decoders for each of them.
• scalers has all the pretrained scalers used in the paper. They are needed to reproduce the experiments.
• notebooks contains all the notebooks required to reproduce the results of the paper.
• dataset contains all the files needed to generate a new dataset.

In order to reproduce the paper results, follow the following procedure:

1. Clone the current repository.

2. Make sure you have all the dependencies listed in requirements.txt. A simple way to do this is to create a virtual environment, e.g. using venv (https://docs.python.org/3/library/venv.html), and download the required dependencies there:

python -m venv radio_map_estimation
source radio_map_estimation/bin/activate
pip install -r respository/requirements.txt

Where radio_map_estimation and respository stand in for the full paths to where you want to save the new virtual environment and where you saved the cloned repository respectively.

3. Download the train, validation, and test datasets from the links (To Do). The downloaded files are tarred and zipped and take about 2 GB, 208 MB, and 215 MB respectively. Their unzipped contents are about 7.36 GB, 819 MB, and 819 MB respectively.

4. To train a model, run Train_Model.ipynb in notebooks and follow instructions there.

5. After training, run Evaluate_Model.ipynb in notebooks. Before execution, specify the path to the model. (To Do)

6. To visualize the results, run Visualize Results.ipynb in notebooks. (To Do)

The paths in every notebook have to be changed according to your file structure.

The code to generate the dataset as well as the dataset itself have been taken from deep-autoencoders-cartography.

Due to the stochastic nature of the data generation process as well as the difference in GPU architectures, your results might vary slightly.