def load_audio_embedding_model_from_path(model_path,
input_repr,
embedding_size,
frontend='kapre'):
"""
Loads a model with weights at the given path.
Parameters
----------
model_path : str
Path to model weights HDF5 (.h5) file. Must be in format
`*._<input_repr>_<content_type>.h5` or
`*._<input_repr>_<content_type>-.*.h5`, since model configuration
will be determined from the filename.
input_repr : "linear", "mel128", or "mel256"
Spectrogram representation used for audio model.
embedding_size : 6144 or 512
Embedding dimensionality.
frontend : "kapre" or "librosa"
The audio frontend to use. If frontend == 'kapre', then the kapre frontend will
be included. Otherwise no frontend will be added inside the keras model.
Returns
-------
model : tf.keras.Model
Model object.
"""
frontend, input_repr = _validate_audio_frontend(frontend, input_repr)
# Construct embedding model and load model weights
with warnings.catch_warnings():
warnings.simplefilter("ignore")
m = AUDIO_MODELS[input_repr](include_frontend=frontend == 'kapre')
m.load_weights(model_path)
# Pooling for final output embedding size
pool_size = AUDIO_POOLING_SIZES[input_repr][embedding_size]
y_a = MaxPooling2D(pool_size=pool_size, padding='same')(m.output)
y_a = Flatten()(y_a)
m = Model(inputs=m.input, outputs=y_a)
m.frontend = frontend
return m
def load_audio_embedding_model(input_repr,
content_type,
embedding_size,
frontend='kapre'):
"""
Returns a model with the given characteristics. Loads the model
if the model has not been loaded yet.
Parameters
----------
input_repr : "linear", "mel128", or "mel256"
Spectrogram representation used for audio model.
content_type : "music" or "env"
Type of content used to train embedding.
embedding_size : 6144 or 512
Embedding dimensionality.
frontend : "kapre" or "librosa"
The audio frontend to use. If frontend == 'kapre', then the kapre frontend will
be included. Otherwise no frontend will be added inside the keras model.
Returns
-------
model : tf.keras.Model
Model object.
"""
frontend, input_repr = _validate_audio_frontend(frontend, input_repr)
# Construct embedding model and load model weights
with warnings.catch_warnings():
warnings.simplefilter("ignore")
m = AUDIO_MODELS[input_repr](include_frontend=frontend == 'kapre')
m.load_weights(get_audio_embedding_model_path(input_repr, content_type))
# Pooling for final output embedding size
pool_size = AUDIO_POOLING_SIZES[input_repr][embedding_size]
y_a = MaxPooling2D(pool_size=pool_size, padding='same')(m.output)
y_a = Flatten()(y_a)
m = Model(inputs=m.input, outputs=y_a)
m.frontend = frontend
return m
