Skip to content

Unable to save converted model locally. #77

@Kheertik

Description

@Kheertik

Hello, I used the code and was able to train a model. When I converted the model from h5 to tflite, it didn't save, and I cannot find it anywhere.

`from tensorflow.keras.models import load_model
from kapre.time_frequency import STFT, Magnitude, ApplyFilterbank, MagnitudeToDecibel
import tensorflow as tf

Load the Keras model

model_path = r'models\lstm.h5' # Using a raw string for Windows path
keras_model = tf.keras.models.load_model(model_path, custom_objects={
'STFT': STFT,
'Magnitude': Magnitude,
'ApplyFilterbank': ApplyFilterbank,
'MagnitudeToDecibel': MagnitudeToDecibel
})

Convert the model to TFLite

converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
tflite_model = converter.convert()

Save the converted model to a .tflite file

tflite_path = r'\models\model.tflite'
with open(tflite_path, 'wb') as f:
f.write(tflite_model)`

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions