Model Archive File¶
The MLTK uses an archive file (
.mltk.zip) to store the relevant model information.
The model archive file is automatically created after running the train command and is updated after running the evaluate, quantize, and update_params commands.
The model archive file uses the standard Zip File Format
and its name has the format:
<model name>.mltk.zip where
<model name> is the name of the MLTK model.
The model archive file is useful as it allows for grouping the various training and evaluation files into a single, distributable file.
This file can also be directly loaded by many MLTK commands and Python APIs, e.g.:
mltk profile ~/my_model.mltk.zip
The model archive file stores a given model’s:
Model specification Python script
Trained model files (
Assume we have the following model archive file
The contents of this archive would have the following contents:
/my_model.py - The model specification script /my_model.tflite - The quantized model which can programmed onto an embedded device /my_model.h5 - The trained, non-quantized, Keras model /my_model.h5.summary.txt - A text summary of the .h5 model /my_model.tflite.summary.txt - A text summary of the .tflite model /train/log.txt - Log file generated during training /train/training-history.png - Training history diagram /train/training-history.json - Training history in JSON format /eval/h5/ - Evaluation results from the .h5 (i.e. non-quantized) model /eval/tflite/ - Evaluation results from the .tflite (i.e. quantized) model