How parthchande/deepsliced-5g works
Project type and purpose
• DeepSliced 5G is a proof-of-concept/demo for 5G network slicing using a deep learning model implemented in a Jupyter Notebook.
• It ingests raw and prefiltered network data, preprocesses it, trains/persists a TensorFlow/Keras model, and runs inference to suggest slice configurations.
File structure
• Top-level files (no subdirectories):
• 5G_Dataset_Network_Slicing_CRAWDAD_Shared.xlsx (raw dataset)
• filtereddata.txt (preprocessed numeric data)
• input_file.csv, test_file.csv (CSV variants)
• Main.ipynb (orchestrates the pipeline)
• README.md, LICENSE
• No backend/frontend separation; this is a single-pipeline AI demo.
README for additional insights
• Confirms a 4-stage flow: Data Preparation → Model Architecture → Training → Inference & Adaptation
• Uses TensorFlow/Keras inside a notebook, with pandas for preprocessing.