ResNet1DArch

class ketos.neural_networks.resnet.ResNet1DArch(*args, **kwargs)[source]

Implements a 1D (temporal) ResNet architecture, building on top of ResNetBlocks.

Args:

block_sets: list of ints: A list specifying the block sets and how many blocks each set contains. Example: [2,2,2] will create a ResNet with 3 block sets, each containing 2 ResNetBlocks (i.e.: a total of 6 residual blocks)
n_classes:int: The number of classes. The output layer uses a Softmax activation and will contain this number of nodes, resulting in model outputs with this many values summing to 1.0.
initial_filters:int: The number of filters used in the first ResNetBlock. Subsequent blocks will have two times more filters than their previous block.
initial_strides: int: Strides used in the first convolutional layer
initial_kernel: int: Kernel size used in the first convolutional layer
strides: int: Strides used in convolutional layers within the blocks
kernel: int: Kernel size used in convolutional layers within the blocks
pre_trained_base: instance of ResNet1DArch: A pre-trained resnet model from which the residual blocks will be taken. Use by the the clone_with_new_top method when creating a clone for transfer learning
batch_norm_momentum: float between 0 and 1: Momentum for the moving average of all the batch normalization layers in the network. The default value is 0.99. For an explanation of how the momentum affects the batch normalisation operation, see <https://www.tensorflow.org/api_docs/python/tf/keras/layers/BatchNormalization>
dropout_rate: float between 0 and 1: Fraction of the input units to drop in all the dropout layers in the network. Set this parameter to 0 to disable dropout (default).

Returns:

A ResNet1DArch object, which is a tensorflow model.

Methods

`call`(inputs[, training])	Calls the model on new inputs.
`clone_with_new_top`([n_classes, freeze_base])	Clone this instance but replace the original classification top with a new (untrained) one
`freeze_block`(block_ids)	Freeze specific residual blocks
`freeze_init_layer`()	Freeze the initial convolutional layer
`freeze_top`()	Freeze the classification block
`get_feature_extraction_base`()	Retrive the feature extraction base (initial convolutional layer + residual blocks)
`set_batch_norm_momentum`(momentum)	Set the momentum for the moving average of all the batch normalization layers in the network.
`set_dropout_rate`(rate)	Set the fraction of the input units to drop in all the dropout layers in the network.
`unfreeze_block`(block_ids)	Unfreeze specific residual blocks
`unfreeze_init_layer`()	Unffreeze the initial convolutional layer
`unfreeze_top`()	Unfreeze the classification block

Attributes

`activity_regularizer`	Optional regularizer function for the output of this layer.
`compute_dtype`	The dtype of the layer's computations.
`distribute_strategy`	The tf.distribute.Strategy this model was created under.
`dtype`	The dtype of the layer weights.
`dtype_policy`	The dtype policy associated with this layer.
`dynamic`	Whether the layer is dynamic (eager-only); set in the constructor.
`inbound_nodes`	Deprecated, do NOT use! Only for compatibility with external Keras.
`input`	Retrieves the input tensor(s) of a layer.
`input_mask`	Retrieves the input mask tensor(s) of a layer.
`input_shape`	Retrieves the input shape(s) of a layer.
`input_spec`	InputSpec instance(s) describing the input format for this layer.
`layers`
`losses`	List of losses added using the add_loss() API.
`metrics`	Returns the model's metrics added using compile(), add_metric() APIs.
`metrics_names`	Returns the model's display labels for all outputs.
`name`	Name of the layer (string), set in the constructor.
`name_scope`	Returns a tf.name_scope instance for this class.
`non_trainable_variables`	Sequence of non-trainable variables owned by this module and its submodules.
`non_trainable_weights`	List of all non-trainable weights tracked by this layer.
`outbound_nodes`	Deprecated, do NOT use! Only for compatibility with external Keras.
`output`	Retrieves the output tensor(s) of a layer.
`output_mask`	Retrieves the output mask tensor(s) of a layer.
`output_shape`	Retrieves the output shape(s) of a layer.
`run_eagerly`	Settable attribute indicating whether the model should run eagerly.
`state_updates`	Deprecated, do NOT use!
`stateful`
`submodules`	Sequence of all sub-modules.
`supports_masking`	Whether this layer supports computing a mask using compute_mask.
`trainable`
`trainable_variables`	Sequence of trainable variables owned by this module and its submodules.
`trainable_weights`	List of all trainable weights tracked by this layer.
`updates`
`variable_dtype`	Alias of Layer.dtype, the dtype of the weights.
`variables`	Returns the list of all layer variables/weights.
`weights`	Returns the list of all layer variables/weights.

call(inputs, training=None)[source]

Calls the model on new inputs.

In this case call just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Args:

inputs: Tensor or list of tensors: A tensor or list of tensors
training: Bool: Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.

Returns:

A tensor if there is a single output, or a list of tensors if there are more than one outputs.

clone_with_new_top(n_classes=None, freeze_base=True)[source]

Clone this instance but replace the original classification top with a new (untrained) one

Args:

n_classes:int: The number of classes the new classification top should output. If None(default), the original number of classes will be used.
freeze_base:bool: If True, the weights of the feature extraction base will be froze (untrainable) in the new model.

Returns:

cloned_model: instance of ResNetArch: The new model with the old feature extraction base and new classification top.

freeze_block(block_ids)[source]

Freeze specific residual blocks

Args:

blocks_ids: list of ints: The block numbers to be freezed (starting from zero)

freeze_init_layer()[source]: Freeze the initial convolutional layer

freeze_top()[source]: Freeze the classification block

get_feature_extraction_base()[source]

Retrive the feature extraction base (initial convolutional layer + residual blocks)

Returns:: list containing the feature extraction layers

set_batch_norm_momentum(momentum)[source]

Set the momentum for the moving average of all the batch normalization layers in the network.

For an explanation of how the momentum affects the batch normalisation operation, see <https://www.tensorflow.org/api_docs/python/tf/keras/layers/BatchNormalization>

Args:

momentum: float between 0 and 1: Momentum for the moving average of the batch normalization layers.

Returns:

None

set_dropout_rate(rate)[source]

Set the fraction of the input units to drop in all the dropout layers in the network.

Args:

rate: float between 0 and 1: Fraction of the input units to drop in the dropout layers.

Returns:

None

unfreeze_block(block_ids)[source]

Unfreeze specific residual blocks

Args:

blocks_ids: list of ints: The block numbers to be freezed (starting from zero)

unfreeze_init_layer()[source]: Unffreeze the initial convolutional layer

unfreeze_top()[source]: Unfreeze the classification block