malrabeiah / camerapredictsbeams Goto Github PK

I am trying to generate the train/validation/test dataset in order to see the dataset in action and I am facing issues. Steps that I am following are the steps provided in the official website and the official paper: https://arxiv.org/pdf/1911.06255.pdf.

Steps that I followed:

    Downloaded the data generation package v1 provided in the official website
    Downloaded the scenario The Distributed-Camera Scenario with Direct View (Single User) (dist_cam) from the official website
    As mentioned in the README file, moved the wireless folder of dataset to RayTracing Scenarios folder and renamed to dist_direct
    In the Dataset_Generator file, the hyperparameters are referenced from Table 1 of the paper https://arxiv.org/pdf/1911.06255.pdf
    Generated the .mat file

In the prep_data_struct.py, getMATLAB function I am giving the path of the generated .mat file but I am getting the following error:

key2 = list(raw_data.keys())
AttributeError: 'Dataset' object has no attribute 'keys'

Also, can you please provide more information about how to generate the codebook? What are the values of the parameters for the UFA_codebook_generator?

Thank you in advance,

Hi, Muhammad, Thanks for this wonderful repo. I have a question. For the scenario 'dist_cam', after downloading the senario data from the ViWi website, how does one detemine (label) the beam index for each RGB image. I run the data_generator for the downloaded wireless data and have channel data for each of three of base station. The channel data is of the shape ( # subcarriers , 5000). I have no idea how to use these data to get the beam idx at a given grid location. Could you kindly elaborate on this? Thanks for you help!