create_model
ADLStream.models.create_model
Creates a deep learning model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
model_architecture |
str |
Model architecture to implemet. |
required |
input_shape |
tuple |
Shape of the input data |
required |
output_size |
int |
Number of neurons of the last layer. |
required |
loss |
tf.keras.Loss |
Loss to be use for training. |
required |
optimizer |
tf.keras.Optimizer |
Optimizer that implements theraining algorithm. |
required |
**args |
specific model parameters. |
{} |
Returns:
Type | Description |
---|---|
tf.keras.Model |
keras model |
Source code in ADLStream/models/model_factory.py
def create_model(model_architecture, input_shape, output_size, loss, optimizer, **args):
"""Creates a deep learning model.
Args:
model_architecture (str): Model architecture to implemet.
input_shape (tuple): Shape of the input data
output_size (int): Number of neurons of the last layer.
loss (tf.keras.Loss): Loss to be use for training.
optimizer (tf.keras.Optimizer): Optimizer that implements theraining algorithm.
**args: specific model parameters.
Returns:
tf.keras.Model: keras model
"""
assert model_architecture.upper() in MODEL_FACTORY, "Model {} not supported".format(
model_architecture
)
return MODEL_FACTORY[model_architecture.upper()](
input_shape, output_size, loss, optimizer, **args
)