How masadipradeeprao/deep_learning_mimo works
The repository combines MATLAB-based DeepMIMO data preparation with a Python beam-selection learning workflow. The documented path is to obtain a DeepMIMO scenario, generate model input/output data, train per-transmitter models, and save predictions and corresponding optimal beams. The tree also contains codebook-generation and hybrid-learning assets, but their runtime connections are not shown. MATLAB source was not excerpted, so those relationships are omitted rather than inferred.
Main entry points: DL_model_python.py Training and evaluation · Generate_DL_data.m DL data generation
Components 17
Dataset preparation
- Dataset generator
DeepMIMOv2/DeepMIMO_Dataset_Generator.m - DeepMIMO generator
DeepMIMOv2/DeepMIMO_functions/DeepMIMO_generator.m - Ray-tracing reader
DeepMIMOv2/DeepMIMO_functions/read_raytracing.m - Channel construction
DeepMIMOv2/DeepMIMO_functions/construct_DeepMIMO_channel.m - Time-domain channel
DeepMIMOv2/DeepMIMO_functions/construct_DeepMIMO_channel_TD.m - User selection
DeepMIMOv2/DeepMIMO_functions/find_users.m - Generator parameters
DeepMIMOv2/DeepMIMO_functions/validate_parameters.m - DL data generation
Deep_learning_MIMO/Generate_DL_data.m
Beamforming assets
- UPA codebook
Deep_learning_MIMO/BF_codebook/UPA_codebook_generator.m - Codebook parameters
Deep_learning_MIMO/CBF_parameters.m - Hybrid learning
Deep_learning_MIMO/Hybrid_Deep_learning.ipynb
Learning workflow
- Input/output data
- Training and evaluation
Deep_learning_MIMO/DL_model_python.py - Per-transmitter models
Deep_learning_MIMO/DL_model_python.py
Evaluation outputs
- Beam predictions
Other components
- Researcher
- DeepMIMO scenario
Connections 8
- Researcher → DeepMIMO scenario: downloads
README.md - Researcher → DL data generation: runs
README.md - DeepMIMO scenario → DL data generation: provides dataset
- DL data generation → Input/output data: generates
README.md - Input/output data → Training and evaluation: loads
Deep_learning_MIMO/DL_model_python.py - Training and evaluation → Per-transmitter models: trains
Deep_learning_MIMO/DL_model_python.py - Training and evaluation → Beam predictions: saves results
Deep_learning_MIMO/DL_model_python.py - Per-transmitter models → Beam predictions: predicts beams
Deep_learning_MIMO/DL_model_python.py