dcase_models.model.VGGish¶
-
class
dcase_models.model.
VGGish
(model=None, model_path=None, metrics=['classification'], n_frames_cnn=96, n_freq_cnn=64, n_classes=10, n_channels=0, embedding_size=128, pooling='avg', include_top=False, compress=False)[source]¶ Bases:
dcase_models.model.container.KerasModelContainer
KerasModelContainer for VGGish model
Jort F. Gemmeke et al. Audio Set: An ontology and human-labeled dataset for audio events International Conference on Acoustics, Speech, and Signal Processing. New Orleans, LA, 2017.
Parameters: - n_frames_cnn : int or None, default=96
Length of the input (number of frames of each sequence).
- n_freq_cnn : int, default=64
Number of frequency bins. The model’s input has shape (n_frames, n_freqs).
- n_classes : int, default=10
Number of classes (dimmension output).
- n_channels : int, default=0
Number of input channels
- 0 : mono signals.
Input shape = (n_frames_cnn, n_freq_cnn)
- 1 : mono signals.
Input shape = (n_frames_cnn, n_freq_cnn, 1)
- 2 : stereo signals.
Input shape = (n_frames_cnn, n_freq_cnn, 2)
- n > 2 : multi-representations.
Input shape = (n_frames_cnn, n_freq_cnn, n_channels)
- embedding_size : int, default=128
Number of units in the embeddings layer.
- pooling : {‘avg’, max}, default=’avg’
Use AveragePooling or Maxpooling.
- include_top : bool, default=False
Include fully-connected layers.
- compress : bool, default=False
Apply PCA.
Notes
https://research.google.com/audioset/ Based on vggish-keras https://pypi.org/project/vggish-keras/
Examples
>>> from dcase_models.model.models import VGGish >>> model_container = VGGish() >>> model_container.model.summary() _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input (InputLayer) (None, 96, 64) 0 _________________________________________________________________ lambda (Lambda) (None, 96, 64, 1) 0 _________________________________________________________________ conv1 (Conv2D) (None, 96, 64, 64) 640 _________________________________________________________________ pool1 (MaxPooling2D) (None, 48, 32, 64) 0 _________________________________________________________________ conv2 (Conv2D) (None, 48, 32, 128) 73856 _________________________________________________________________ pool2 (MaxPooling2D) (None, 24, 16, 128) 0 _________________________________________________________________ conv3/conv3_1 (Conv2D) (None, 24, 16, 256) 295168 _________________________________________________________________ conv3/conv3_2 (Conv2D) (None, 24, 16, 256) 590080 _________________________________________________________________ pool3 (MaxPooling2D) (None, 12, 8, 256) 0 _________________________________________________________________ conv4/conv4_1 (Conv2D) (None, 12, 8, 512) 1180160 _________________________________________________________________ conv4/conv4_2 (Conv2D) (None, 12, 8, 512) 2359808 _________________________________________________________________ pool4 (MaxPooling2D) (None, 6, 4, 512) 0 _________________________________________________________________ global_average_pooling2d_1 ( (None, 512) 0 ================================================================= Total params: 4,499,712 Trainable params: 4,499,712 Non-trainable params: 0 _________________________________________________________________
Attributes: - model : keras.models.Model
Keras model.
-
__init__
(model=None, model_path=None, metrics=['classification'], n_frames_cnn=96, n_freq_cnn=64, n_classes=10, n_channels=0, embedding_size=128, pooling='avg', include_top=False, compress=False)[source]¶ Initialize ModelContainer
Parameters: - model : keras model or similar
Object that defines the model (i.e keras.models.Model)
- model_path : str
Path to the model file
- model_name : str
Model name
- metrics : list of str
List of metrics used for evaluation
Methods
__init__
([model, model_path, metrics, …])Initialize ModelContainer build
()Builds the VGGish Keras model. check_if_model_exists
(folder, **kwargs)Checks if the model already exits in the path. cut_network
(layer_where_to_cut)Cuts the network at the layer passed as argument. download_pretrained_weights
([weights_folder])Download pretrained weights from: https://github.com/DTaoo/VGGish https://drive.google.com/file/d/1mhqXZ8CANgHyepum7N4yrjiyIg6qaMe6/view evaluate
(data_test, **kwargs)Evaluates the keras model using X_test and Y_test. fine_tuning
(layer_where_to_cut[, …])Create a new model for fine-tuning. get_available_intermediate_outputs
()Return a list of available intermediate outputs. get_intermediate_output
(output_ix_name, inputs)Return the output of the model in a given layer. get_number_of_parameters
()Missing docstring here load_model_from_json
(folder, **kwargs)Loads a model from a model.json file in the path given by folder. load_model_weights
(weights_folder)Loads self.model weights in weights_folder/best_weights.hdf5. load_pretrained_model_weights
([weights_folder])Loads pretrained weights to self.model weights. save_model_json
(folder)Saves the model to a model.json file in the given folder path. save_model_weights
(weights_folder)Saves self.model weights in weights_folder/best_weights.hdf5. train
(data_train, data_val[, weights_path, …])Trains the keras model using the data and paramaters of arguments. -
class
Postprocess
(output_shape=None, **kw)[source]¶ Bases:
tensorflow.python.keras.engine.base_layer.Layer
Keras layer that applies PCA and quantizes the ouput.
Based on vggish-keras https://pypi.org/project/vggish-keras/
-
activity_regularizer
¶ Optional regularizer function for the output of this layer.
-
add_loss
(losses, **kwargs)¶ Add loss tensor(s), potentially dependent on layer inputs.
Some losses (for instance, activity regularization losses) may be dependent on the inputs passed when calling a layer. Hence, when reusing the same layer on different inputs a and b, some entries in layer.losses may be dependent on a and some on b. This method automatically keeps track of dependencies.
This method can be used inside a subclassed layer or model’s call function, in which case losses should be a Tensor or list of Tensors.
Example:
```python class MyLayer(tf.keras.layers.Layer):
- def call(self, inputs):
- self.add_loss(tf.abs(tf.reduce_mean(inputs))) return inputs
This method can also be called directly on a Functional Model during construction. In this case, any loss Tensors passed to this Model must be symbolic and be able to be traced back to the model’s Input`s. These losses become part of the model’s topology and are tracked in `get_config.
Example:
`python inputs = tf.keras.Input(shape=(10,)) x = tf.keras.layers.Dense(10)(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) # Activity regularization. model.add_loss(tf.abs(tf.reduce_mean(x))) `
If this is not the case for your loss (if, for example, your loss references a Variable of one of the model’s layers), you can wrap your loss in a zero-argument lambda. These losses are not tracked as part of the model’s topology since they can’t be serialized.
Example:
`python inputs = tf.keras.Input(shape=(10,)) d = tf.keras.layers.Dense(10) x = d(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) # Weight regularization. model.add_loss(lambda: tf.reduce_mean(d.kernel)) `
- Arguments:
- losses: Loss tensor, or list/tuple of tensors. Rather than tensors, losses
- may also be zero-argument callables which create a loss tensor.
- **kwargs: Additional keyword arguments for backward compatibility.
- Accepted values:
- inputs - Deprecated, will be automatically inferred.
-
add_metric
(value, name=None, **kwargs)¶ Adds metric tensor to the layer.
This method can be used inside the call() method of a subclassed layer or model.
```python class MyMetricLayer(tf.keras.layers.Layer):
- def __init__(self):
- super(MyMetricLayer, self).__init__(name=’my_metric_layer’) self.mean = tf.keras.metrics.Mean(name=’metric_1’)
- def call(self, inputs):
- self.add_metric(self.mean(x)) self.add_metric(tf.reduce_sum(x), name=’metric_2’) return inputs
This method can also be called directly on a Functional Model during construction. In this case, any tensor passed to this Model must be symbolic and be able to be traced back to the model’s Input`s. These metrics become part of the model’s topology and are tracked when you save the model via `save().
`python inputs = tf.keras.Input(shape=(10,)) x = tf.keras.layers.Dense(10)(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) model.add_metric(math_ops.reduce_sum(x), name='metric_1') `
Note: Calling add_metric() with the result of a metric object on a Functional Model, as shown in the example below, is not supported. This is because we cannot trace the metric result tensor back to the model’s inputs.
`python inputs = tf.keras.Input(shape=(10,)) x = tf.keras.layers.Dense(10)(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) model.add_metric(tf.keras.metrics.Mean()(x), name='metric_1') `
- Args:
value: Metric tensor. name: String metric name. **kwargs: Additional keyword arguments for backward compatibility.
Accepted values: aggregation - When the value tensor provided is not the result of calling a keras.Metric instance, it will be aggregated by default using a keras.Metric.Mean.
-
add_update
(updates, inputs=None)¶ Add update op(s), potentially dependent on layer inputs.
Weight updates (for instance, the updates of the moving mean and variance in a BatchNormalization layer) may be dependent on the inputs passed when calling a layer. Hence, when reusing the same layer on different inputs a and b, some entries in layer.updates may be dependent on a and some on b. This method automatically keeps track of dependencies.
This call is ignored when eager execution is enabled (in that case, variable updates are run on the fly and thus do not need to be tracked for later execution).
- Arguments:
- updates: Update op, or list/tuple of update ops, or zero-arg callable
- that returns an update op. A zero-arg callable should be passed in order to disable running the updates by setting trainable=False on this Layer, when executing in Eager mode.
inputs: Deprecated, will be automatically inferred.
-
add_variable
(*args, **kwargs)¶ Deprecated, do NOT use! Alias for add_weight.
-
add_weight
(name=None, shape=None, dtype=None, initializer=None, regularizer=None, trainable=None, constraint=None, use_resource=None, synchronization=<VariableSynchronization.AUTO: 0>, aggregation=<VariableAggregation.NONE: 0>, **kwargs)¶ Adds a new variable to the layer.
- Arguments:
name: Variable name. shape: Variable shape. Defaults to scalar if unspecified. dtype: The type of the variable. Defaults to self.dtype. initializer: Initializer instance (callable). regularizer: Regularizer instance (callable). trainable: Boolean, whether the variable should be part of the layer’s
“trainable_variables” (e.g. variables, biases) or “non_trainable_variables” (e.g. BatchNorm mean and variance). Note that trainable cannot be True if synchronization is set to ON_READ.constraint: Constraint instance (callable). use_resource: Whether to use ResourceVariable. synchronization: Indicates when a distributed a variable will be
aggregated. Accepted values are constants defined in the class tf.VariableSynchronization. By default the synchronization is set to AUTO and the current DistributionStrategy chooses when to synchronize. If synchronization is set to ON_READ, trainable must not be set to True.- aggregation: Indicates how a distributed variable will be aggregated.
- Accepted values are constants defined in the class tf.VariableAggregation.
- **kwargs: Additional keyword arguments. Accepted values are getter,
- collections, experimental_autocast and caching_device.
- Returns:
- The variable created.
- Raises:
- ValueError: When giving unsupported dtype and no initializer or when
- trainable has been set to True with synchronization set as ON_READ.
-
apply
(inputs, *args, **kwargs)¶ Deprecated, do NOT use!
This is an alias of self.__call__.
-
build
(input_shape)[source]¶ Creates the variables of the layer (optional, for subclass implementers).
This is a method that implementers of subclasses of Layer or Model can override if they need a state-creation step in-between layer instantiation and layer call.
This is typically used to create the weights of Layer subclasses.
- Arguments:
- input_shape: Instance of TensorShape, or list of instances of
- TensorShape if the layer expects a list of inputs (one instance per input).
-
call
(x)[source]¶ This is where the layer’s logic lives.
Note here that call() method in tf.keras is little bit different from keras API. In keras API, you can pass support masking for layers as additional arguments. Whereas tf.keras has compute_mask() method to support masking.
- Arguments:
- inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments. Currently unused.
- Returns:
- A tensor or list/tuple of tensors.
-
compute_dtype
¶ The dtype of the layer’s computations.
This is equivalent to Layer.dtype_policy.compute_dtype. Unless mixed precision is used, this is the same as Layer.dtype, the dtype of the weights.
Layers automatically cast their inputs to the compute dtype, which causes computations and the output to be in the compute dtype as well. This is done by the base Layer class in Layer.__call__, so you do not have to insert these casts if implementing your own layer.
Layers often perform certain internal computations in higher precision when compute_dtype is float16 or bfloat16 for numeric stability. The output will still typically be float16 or bfloat16 in such cases.
- Returns:
- The layer’s compute dtype.
-
compute_mask
(inputs, mask=None)¶ Computes an output mask tensor.
- Arguments:
- inputs: Tensor or list of tensors. mask: Tensor or list of tensors.
- Returns:
- None or a tensor (or list of tensors,
- one per output tensor of the layer).
-
compute_output_shape
(input_shape)¶ Computes the output shape of the layer.
If the layer has not been built, this method will call build on the layer. This assumes that the layer will later be used with inputs that match the input shape provided here.
- Arguments:
- input_shape: Shape tuple (tuple of integers)
- or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
- Returns:
- An input shape tuple.
-
compute_output_signature
(input_signature)¶ Compute the output tensor signature of the layer based on the inputs.
Unlike a TensorShape object, a TensorSpec object contains both shape and dtype information for a tensor. This method allows layers to provide output dtype information if it is different from the input dtype. For any layer that doesn’t implement this function, the framework will fall back to use compute_output_shape, and will assume that the output dtype matches the input dtype.
- Args:
- input_signature: Single TensorSpec or nested structure of TensorSpec
- objects, describing a candidate input for the layer.
- Returns:
- Single TensorSpec or nested structure of TensorSpec objects, describing
- how the layer would transform the provided input.
- Raises:
- TypeError: If input_signature contains a non-TensorSpec object.
-
count_params
()¶ Count the total number of scalars composing the weights.
- Returns:
- An integer count.
- Raises:
- ValueError: if the layer isn’t yet built
- (in which case its weights aren’t yet defined).
-
dtype
¶ The dtype of the layer weights.
This is equivalent to Layer.dtype_policy.variable_dtype. Unless mixed precision is used, this is the same as Layer.compute_dtype, the dtype of the layer’s computations.
-
dtype_policy
¶ The dtype policy associated with this layer.
This is an instance of a tf.keras.mixed_precision.Policy.
-
dynamic
¶ Whether the layer is dynamic (eager-only); set in the constructor.
-
classmethod
from_config
(config)¶ Creates a layer from its config.
This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).
- Arguments:
- config: A Python dictionary, typically the
- output of get_config.
- Returns:
- A layer instance.
-
get_config
()¶ Returns the config of the layer.
A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.
The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).
- Returns:
- Python dictionary.
-
get_input_at
(node_index)¶ Retrieves the input tensor(s) of a layer at a given node.
- Arguments:
- node_index: Integer, index of the node
- from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.
- Returns:
- A tensor (or list of tensors if the layer has multiple inputs).
- Raises:
- RuntimeError: If called in Eager mode.
-
get_input_mask_at
(node_index)¶ Retrieves the input mask tensor(s) of a layer at a given node.
- Arguments:
- node_index: Integer, index of the node
- from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.
- Returns:
- A mask tensor (or list of tensors if the layer has multiple inputs).
-
get_input_shape_at
(node_index)¶ Retrieves the input shape(s) of a layer at a given node.
- Arguments:
- node_index: Integer, index of the node
- from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.
- Returns:
- A shape tuple (or list of shape tuples if the layer has multiple inputs).
- Raises:
- RuntimeError: If called in Eager mode.
-
get_losses_for
(inputs)¶ Deprecated, do NOT use!
Retrieves losses relevant to a specific set of inputs.
- Arguments:
- inputs: Input tensor or list/tuple of input tensors.
- Returns:
- List of loss tensors of the layer that depend on inputs.
-
get_output_at
(node_index)¶ Retrieves the output tensor(s) of a layer at a given node.
- Arguments:
- node_index: Integer, index of the node
- from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.
- Returns:
- A tensor (or list of tensors if the layer has multiple outputs).
- Raises:
- RuntimeError: If called in Eager mode.
-
get_output_mask_at
(node_index)¶ Retrieves the output mask tensor(s) of a layer at a given node.
- Arguments:
- node_index: Integer, index of the node
- from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.
- Returns:
- A mask tensor (or list of tensors if the layer has multiple outputs).
-
get_output_shape_at
(node_index)¶ Retrieves the output shape(s) of a layer at a given node.
- Arguments:
- node_index: Integer, index of the node
- from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.
- Returns:
- A shape tuple (or list of shape tuples if the layer has multiple outputs).
- Raises:
- RuntimeError: If called in Eager mode.
-
get_updates_for
(inputs)¶ Deprecated, do NOT use!
Retrieves updates relevant to a specific set of inputs.
- Arguments:
- inputs: Input tensor or list/tuple of input tensors.
- Returns:
- List of update ops of the layer that depend on inputs.
-
get_weights
()¶ Returns the current weights of the layer.
The weights of a layer represent the state of the layer. This function returns both trainable and non-trainable weight values associated with this layer as a list of Numpy arrays, which can in turn be used to load state into similarly parameterized layers.
For example, a Dense layer returns a list of two values– per-output weights and the bias value. These can be used to set the weights of another Dense layer:
>>> a = tf.keras.layers.Dense(1, ... kernel_initializer=tf.constant_initializer(1.)) >>> a_out = a(tf.convert_to_tensor([[1., 2., 3.]])) >>> a.get_weights() [array([[1.], [1.], [1.]], dtype=float32), array([0.], dtype=float32)] >>> b = tf.keras.layers.Dense(1, ... kernel_initializer=tf.constant_initializer(2.)) >>> b_out = b(tf.convert_to_tensor([[10., 20., 30.]])) >>> b.get_weights() [array([[2.], [2.], [2.]], dtype=float32), array([0.], dtype=float32)] >>> b.set_weights(a.get_weights()) >>> b.get_weights() [array([[1.], [1.], [1.]], dtype=float32), array([0.], dtype=float32)]
- Returns:
- Weights values as a list of numpy arrays.
-
inbound_nodes
¶ Deprecated, do NOT use! Only for compatibility with external Keras.
-
input
¶ Retrieves the input tensor(s) of a layer.
Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer.
- Returns:
- Input tensor or list of input tensors.
- Raises:
- RuntimeError: If called in Eager mode. AttributeError: If no inbound nodes are found.
-
input_mask
¶ Retrieves the input mask tensor(s) of a layer.
Only applicable if the layer has exactly one inbound node, i.e. if it is connected to one incoming layer.
- Returns:
- Input mask tensor (potentially None) or list of input mask tensors.
- Raises:
- AttributeError: if the layer is connected to more than one incoming layers.
-
input_shape
¶ Retrieves the input shape(s) of a layer.
Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer, or if all inputs have the same shape.
- Returns:
- Input shape, as an integer shape tuple (or list of shape tuples, one tuple per input tensor).
- Raises:
- AttributeError: if the layer has no defined input_shape. RuntimeError: if called in Eager mode.
-
input_spec
¶ InputSpec instance(s) describing the input format for this layer.
When you create a layer subclass, you can set self.input_spec to enable the layer to run input compatibility checks when it is called. Consider a Conv2D layer: it can only be called on a single input tensor of rank 4. As such, you can set, in __init__():
`python self.input_spec = tf.keras.layers.InputSpec(ndim=4) `
Now, if you try to call the layer on an input that isn’t rank 4 (for instance, an input of shape (2,), it will raise a nicely-formatted error:
` ValueError: Input 0 of layer conv2d is incompatible with the layer: expected ndim=4, found ndim=1. Full shape received: [2] `
Input checks that can be specified via input_spec include: - Structure (e.g. a single input, a list of 2 inputs, etc) - Shape - Rank (ndim) - Dtype
For more information, see tf.keras.layers.InputSpec.
- Returns:
- A tf.keras.layers.InputSpec instance, or nested structure thereof.
-
losses
¶ List of losses added using the add_loss() API.
Variable regularization tensors are created when this property is accessed, so it is eager safe: accessing losses under a tf.GradientTape will propagate gradients back to the corresponding variables.
Examples:
>>> class MyLayer(tf.keras.layers.Layer): ... def call(self, inputs): ... self.add_loss(tf.abs(tf.reduce_mean(inputs))) ... return inputs >>> l = MyLayer() >>> l(np.ones((10, 1))) >>> l.losses [1.0]
>>> inputs = tf.keras.Input(shape=(10,)) >>> x = tf.keras.layers.Dense(10)(inputs) >>> outputs = tf.keras.layers.Dense(1)(x) >>> model = tf.keras.Model(inputs, outputs) >>> # Activity regularization. >>> len(model.losses) 0 >>> model.add_loss(tf.abs(tf.reduce_mean(x))) >>> len(model.losses) 1
>>> inputs = tf.keras.Input(shape=(10,)) >>> d = tf.keras.layers.Dense(10, kernel_initializer='ones') >>> x = d(inputs) >>> outputs = tf.keras.layers.Dense(1)(x) >>> model = tf.keras.Model(inputs, outputs) >>> # Weight regularization. >>> model.add_loss(lambda: tf.reduce_mean(d.kernel)) >>> model.losses [<tf.Tensor: shape=(), dtype=float32, numpy=1.0>]
- Returns:
- A list of tensors.
-
metrics
¶ List of metrics added using the add_metric() API.
Example:
>>> input = tf.keras.layers.Input(shape=(3,)) >>> d = tf.keras.layers.Dense(2) >>> output = d(input) >>> d.add_metric(tf.reduce_max(output), name='max') >>> d.add_metric(tf.reduce_min(output), name='min') >>> [m.name for m in d.metrics] ['max', 'min']
- Returns:
- A list of Metric objects.
-
name
¶ Name of the layer (string), set in the constructor.
-
name_scope
¶ Returns a tf.name_scope instance for this class.
-
non_trainable_variables
¶
-
non_trainable_weights
¶ List of all non-trainable weights tracked by this layer.
Non-trainable weights are not updated during training. They are expected to be updated manually in call().
Note: This will not track the weights of nested tf.Modules that are not themselves Keras layers.
- Returns:
- A list of non-trainable variables.
-
outbound_nodes
¶ Deprecated, do NOT use! Only for compatibility with external Keras.
-
output
¶ Retrieves the output tensor(s) of a layer.
Only applicable if the layer has exactly one output, i.e. if it is connected to one incoming layer.
- Returns:
- Output tensor or list of output tensors.
- Raises:
- AttributeError: if the layer is connected to more than one incoming
- layers.
RuntimeError: if called in Eager mode.
-
output_mask
¶ Retrieves the output mask tensor(s) of a layer.
Only applicable if the layer has exactly one inbound node, i.e. if it is connected to one incoming layer.
- Returns:
- Output mask tensor (potentially None) or list of output mask tensors.
- Raises:
- AttributeError: if the layer is connected to more than one incoming layers.
-
output_shape
¶ Retrieves the output shape(s) of a layer.
Only applicable if the layer has one output, or if all outputs have the same shape.
- Returns:
- Output shape, as an integer shape tuple (or list of shape tuples, one tuple per output tensor).
- Raises:
- AttributeError: if the layer has no defined output shape. RuntimeError: if called in Eager mode.
-
set_weights
(weights)¶ Sets the weights of the layer, from Numpy arrays.
The weights of a layer represent the state of the layer. This function sets the weight values from numpy arrays. The weight values should be passed in the order they are created by the layer. Note that the layer’s weights must be instantiated before calling this function by calling the layer.
For example, a Dense layer returns a list of two values– per-output weights and the bias value. These can be used to set the weights of another Dense layer:
>>> a = tf.keras.layers.Dense(1, ... kernel_initializer=tf.constant_initializer(1.)) >>> a_out = a(tf.convert_to_tensor([[1., 2., 3.]])) >>> a.get_weights() [array([[1.], [1.], [1.]], dtype=float32), array([0.], dtype=float32)] >>> b = tf.keras.layers.Dense(1, ... kernel_initializer=tf.constant_initializer(2.)) >>> b_out = b(tf.convert_to_tensor([[10., 20., 30.]])) >>> b.get_weights() [array([[2.], [2.], [2.]], dtype=float32), array([0.], dtype=float32)] >>> b.set_weights(a.get_weights()) >>> b.get_weights() [array([[1.], [1.], [1.]], dtype=float32), array([0.], dtype=float32)]
- Arguments:
- weights: a list of Numpy arrays. The number
- of arrays and their shape must match number of the dimensions of the weights of the layer (i.e. it should match the output of get_weights).
- Raises:
- ValueError: If the provided weights list does not match the
- layer’s specifications.
-
stateful
¶
-
submodules
¶ Sequence of all sub-modules.
Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).
>>> a = tf.Module() >>> b = tf.Module() >>> c = tf.Module() >>> a.b = b >>> b.c = c >>> list(a.submodules) == [b, c] True >>> list(b.submodules) == [c] True >>> list(c.submodules) == [] True
- Returns:
- A sequence of all submodules.
-
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.
Note: this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don’t expect the return value to change.
- Returns:
- A sequence of variables for the current module (sorted by attribute name) followed by variables from all submodules recursively (breadth first).
-
trainable_weights
¶ List of all trainable weights tracked by this layer.
Trainable weights are updated via gradient descent during training.
Note: This will not track the weights of nested tf.Modules that are not themselves Keras layers.
- Returns:
- A list of trainable variables.
-
updates
¶
-
variable_dtype
¶ Alias of Layer.dtype, the dtype of the weights.
-
variables
¶ Returns the list of all layer variables/weights.
Alias of self.weights.
Note: This will not track the weights of nested tf.Modules that are not themselves Keras layers.
- Returns:
- A list of variables.
-
weights
¶ Returns the list of all layer variables/weights.
Note: This will not track the weights of nested tf.Modules that are not themselves Keras layers.
- Returns:
- A list of variables.
-
classmethod
with_name_scope
(method)¶ Decorator to automatically enter the module name scope.
>>> class MyModule(tf.Module): ... @tf.Module.with_name_scope ... def __call__(self, x): ... if not hasattr(self, 'w'): ... self.w = tf.Variable(tf.random.normal([x.shape[1], 3])) ... return tf.matmul(x, self.w)
Using the above module would produce `tf.Variable`s and `tf.Tensor`s whose names included the module name:
>>> mod = MyModule() >>> mod(tf.ones([1, 2])) <tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)> >>> mod.w <tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32, numpy=..., dtype=float32)>
- Args:
- method: The method to wrap.
- Returns:
- The original method wrapped such that it enters the module’s name scope.
-
-
check_if_model_exists
(folder, **kwargs)¶ Checks if the model already exits in the path.
Check if the folder/model.json file exists and includes the same model as self.model.
Parameters: - folder : str
Path to the folder to check.
-
cut_network
(layer_where_to_cut)¶ Cuts the network at the layer passed as argument.
Parameters: - layer_where_to_cut : str or int
Layer name (str) or index (int) where cut the model.
Returns: - keras.models.Model
Cutted model.
-
download_pretrained_weights
(weights_folder='./pretrained_weights')[source]¶ Download pretrained weights from: https://github.com/DTaoo/VGGish https://drive.google.com/file/d/1mhqXZ8CANgHyepum7N4yrjiyIg6qaMe6/view
Code based on: https://github.com/beasteers/VGGish/blob/master/vggish_keras/download_helpers/download_weights.py
Parameters: - weights_folder : str
Path to save the weights file
-
evaluate
(data_test, **kwargs)¶ Evaluates the keras model using X_test and Y_test.
Parameters: - X_test : ndarray
3D array with mel-spectrograms of test set. Shape = (N_instances, N_hops, N_mel_bands)
- Y_test : ndarray
2D array with the annotations of test set (one hot encoding). Shape (N_instances, N_classes)
- scaler : Scaler, optional
Scaler objet to be applied if is not None.
Returns: - float
evaluation’s accuracy
- list
list of annotations (ground_truth)
- list
list of model predictions
-
fine_tuning
(layer_where_to_cut, new_number_of_classes=10, new_activation='softmax', freeze_source_model=True, new_model=None)¶ Create a new model for fine-tuning.
Cut the model in the layer_where_to_cut layer and add a new fully-connected layer.
Parameters: - layer_where_to_cut : str or int
Name (str) of index (int) of the layer where cut the model. This layer is included in the new model.
- new_number_of_classes : int
Number of units in the new fully-connected layer (number of classes).
- new_activation : str
Activation of the new fully-connected layer.
- freeze_source_model : bool
If True, the source model is set to not be trainable.
- new_model : Keras Model
If is not None, this model is added after the cut model. This is useful if you want add more than a fully-connected layer.
-
get_available_intermediate_outputs
()¶ Return a list of available intermediate outputs.
Return a list of model’s layers.
Returns: - list of str
List of layers names.
-
get_intermediate_output
(output_ix_name, inputs)¶ Return the output of the model in a given layer.
Cut the model in the given layer and predict the output for the given inputs.
Returns: - ndarray
Output of the model in the given layer.
-
get_number_of_parameters
()¶ Missing docstring here
-
load_model_from_json
(folder, **kwargs)¶ Loads a model from a model.json file in the path given by folder. The model is load in self.model attribute.
Parameters: - folder : str
Path to the folder that contains model.json file
-
load_model_weights
(weights_folder)¶ Loads self.model weights in weights_folder/best_weights.hdf5.
Parameters: - weights_folder : str
Path to save the weights file.
-
load_pretrained_model_weights
(weights_folder='./pretrained_weights')[source]¶ Loads pretrained weights to self.model weights.
Parameters: - weights_folder : str
Path to load the weights file
-
save_model_json
(folder)¶ Saves the model to a model.json file in the given folder path.
Parameters: - folder : str
Path to the folder to save model.json file
-
save_model_weights
(weights_folder)¶ Saves self.model weights in weights_folder/best_weights.hdf5.
Parameters: - weights_folder : str
Path to save the weights file
-
train
(data_train, data_val, weights_path='./', optimizer='Adam', learning_rate=0.001, early_stopping=100, considered_improvement=0.01, losses='categorical_crossentropy', loss_weights=[1], sequence_time_sec=0.5, metric_resolution_sec=1.0, label_list=[], shuffle=True, **kwargs_keras_fit)¶ Trains the keras model using the data and paramaters of arguments.
Parameters: - X_train : ndarray
3D array with mel-spectrograms of train set. Shape = (N_instances, N_hops, N_mel_bands)
- Y_train : ndarray
2D array with the annotations of train set (one hot encoding). Shape (N_instances, N_classes)
- X_val : ndarray
3D array with mel-spectrograms of validation set. Shape = (N_instances, N_hops, N_mel_bands)
- Y_val : ndarray
2D array with the annotations of validation set (one hot encoding). Shape (N_instances, N_classes)
- weights_path : str
Path where to save the best weights of the model in the training process
- weights_path : str
Path where to save log of the training process
- loss_weights : list
List of weights for each loss function (‘categorical_crossentropy’, ‘mean_squared_error’, ‘prototype_loss’)
- optimizer : str
Optimizer used to train the model
- learning_rate : float
Learning rate used to train the model
- batch_size : int
Batch size used in the training process
- epochs : int
Number of training epochs
- fit_verbose : int
Verbose mode for fit method of Keras model