Class ConvLSTM2D

Convolutional LSTM. It is similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.

Inheritance

System.Object

Keras

Base

BaseLayer

RNN

ConvLSTM2D

Implements

System.IDisposable

Inherited Members

BaseLayer.Set(BaseLayer[])

Base.Parameters

Base.None

Base.Init()

Base.ToPython()

Base.InvokeStaticMethod(Object, String, Dictionary<String, Object>)

Base.InvokeMethod(String, Dictionary<String, Object>)

Base.Item[String]

Keras.Instance

Keras.keras

Keras.keras2onnx

Keras.tfjs

Keras.Dispose()

Keras.ToTuple(Array)

Keras.ToList(Array)

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: Keras.Layers

Assembly: Keras.dll

Syntax

public class ConvLSTM2D : RNN, IDisposable

Constructors

ConvLSTM2D(Int32, Tuple<Int32, Int32>, Tuple<Int32, Int32>, String, String, Tuple<Int32, Int32>, String, String, Boolean, String, String, String, Boolean, String, String, String, String, String, String, String, Boolean, Boolean, Boolean, Single, Single, Shape)

Initializes a new instance of the ConvLSTM2D class.

Declaration

public ConvLSTM2D(int filters, Tuple<int, int> kernel_size, Tuple<int, int> strides = null, string padding = "valid", string data_format = "", Tuple<int, int> dilation_rate = null, string activation = "tanh", string recurrent_activation = "hard_sigmoid", bool use_bias = true, string kernel_initializer = "glorot_uniform", string recurrent_initializer = "orthogonal", string bias_initializer = "zeros", bool unit_forget_bias = true, string kernel_regularizer = "", string recurrent_regularizer = "", string bias_regularizer = "", string activity_regularizer = "", string kernel_constraint = "", string recurrent_constraint = "", string bias_constraint = "", bool return_sequences = false, bool go_backwards = false, bool stateful = false, float dropout = 0F, float recurrent_dropout = 0F, Shape input_shape = null)

Parameters

Type	Name	Description
System.Int32	filters	Integer, the dimensionality of the output space (i.e. the number output of filters in the convolution).
System.Tuple<System.Int32, System.Int32>	kernel_size	An integer or tuple/list of n integers, specifying the dimensions of the convolution window.
System.Tuple<System.Int32, System.Int32>	strides	An integer or tuple/list of n integers, specifying the strides of the convolution. Specifying any stride value != 1 is incompatible with specifying any dilation_rate value != 1.
System.String	padding	One of "valid" or "same" (case-insensitive).
System.String	data_format	A string, one of "channels_last" (default) or "channels_first". The ordering of the dimensions in the inputs. "channels_last" corresponds to inputs with shape (batch, time, ..., channels) while "channels_first" corresponds to inputs with shape (batch, time, channels, ...). It defaults to the image_data_format value found in your Keras config file at ~/.keras/keras.json. If you never set it, then it will be "channels_last".
System.Tuple<System.Int32, System.Int32>	dilation_rate	An integer or tuple/list of n integers, specifying the dilation rate to use for dilated convolution. Currently, specifying any dilation_rate value != 1 is incompatible with specifying any strides value != 1.
System.String	activation	Activation function to use (see activations). If you don't specify anything, no activation is applied (ie. "linear" activation: a(x) = x).
System.String	recurrent_activation	Activation function to use for the recurrent step (see activations).
System.Boolean	use_bias	Boolean, whether the layer uses a bias vector.
System.String	kernel_initializer	Initializer for the kernel weights matrix, used for the linear transformation of the inputs. (see initializers).
System.String	recurrent_initializer	Initializer for the recurrent_kernel weights matrix, used for the linear transformation of the recurrent state. (see initializers).
System.String	bias_initializer	Initializer for the bias vector (see initializers).
System.Boolean	unit_forget_bias	Boolean. If True, add 1 to the bias of the forget gate at initialization. Use in combination with bias_initializer="zeros". This is recommended in Jozefowicz et al. (2015).
System.String	kernel_regularizer	Regularizer function applied to the kernel weights matrix (see regularizer).
System.String	recurrent_regularizer	Regularizer function applied to the recurrent_kernel weights matrix (see regularizer).
System.String	bias_regularizer	Regularizer function applied to the bias vector (see regularizer).
System.String	activity_regularizer	Regularizer function applied to the output of the layer (its "activation"). (see regularizer).
System.String	kernel_constraint	Constraint function applied to the kernel weights matrix (see constraints).
System.String	recurrent_constraint	Constraint function applied to the recurrent_kernel weights matrix (see constraints).
System.String	bias_constraint	Constraint function applied to the bias vector (see constraints).
System.Boolean	return_sequences	Boolean. Whether to return the last output in the output sequence, or the full sequence.
System.Boolean	go_backwards	Boolean (default False). If True, process the input sequence backwards.
System.Boolean	stateful	Boolean (default False). If True, the last state for each sample at index i in a batch will be used as initial state for the sample of index i in the following batch.
System.Single	dropout	Float between 0 and 1. Fraction of the units to drop for the linear transformation of the inputs.
System.Single	recurrent_dropout	Float between 0 and 1. Fraction of the units to drop for the linear transformation of the recurrent state.
Shape	input_shape	The input shape.

Implements

System.IDisposable