ML_Gearbox_Fault_Diagnosis

• A "Hello world" example of tiny ml.
• This dataset is from https://www.kaggle.com/datasets/brjapon/gearbox-fault-diagnosis.
• We provide an example training script for this dataset, as well as code for converting it to TFLite and C source code.

1. First step

1. Install virtual env

• If you haven't installed NuEdgeWise, please follow these steps to install Python virtual environment and choose NuEdgeWise_env.
• Skip if you have done.

2. Running

• The dnn.ipynb or autoencoder.ipynb notebooks will assist you in preparing the data, training the model, and finally converting it to TFLite and C++ files.

2. Inference code

• The ML_SampleCode repositories are private. Please contact Nuvoton to request access to these sample codes. Link
  • ML_M460_SampleCode (private repo)
    • tflu_gearbox_samplecode