Attention: This MediaPipe Solutions Preview is an early release. Learn more.


Stay organized with collections Save and categorize content based on your preferences.

The abstract base class that represents a custom TensorFlow model.

model_spec Specification for the model.
shuffle Whether the training data need be shuffled.



View source

Evaluates the model with the provided data.


View source

Converts the model to requested formats.

export_dir The directory to save exported files.
tflite_filename File name to save TFLite model. The full export path is {export_dir}/{tflite_filename}.
quantization_config The configuration for model quantization.
preprocess A callable to preprocess the representative dataset for quantization. The callable takes three arguments in order: feature, label, and is_training.


View source

Prints a summary of the model.