Type ConvLSTM2D
Namespace tensorflow.keras.layers
Parent ConvRNN2D
Interfaces IConvLSTM2D
Convolutional LSTM. It is similar to an LSTM layer, but the input transformations
and recurrent transformations are both convolutional.
Methods
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call__
- __call___dyn
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call
- call_dyn
- call_dyn
- compute_output_shape
- compute_output_shape
- compute_output_shape
- get_initial_state
- get_initial_state
- get_initial_state_dyn
- NewDyn
- reset_states
- reset_states
- reset_states
- reset_states_dyn
Properties
- activation
- activation_dyn
- activity_regularizer
- activity_regularizer_dyn
- bias_constraint
- bias_constraint_dyn
- bias_initializer
- bias_initializer_dyn
- bias_regularizer
- bias_regularizer_dyn
- built
- cell
- constants_spec
- data_format
- data_format_dyn
- dilation_rate
- dilation_rate_dyn
- dropout
- dropout_dyn
- dtype
- dtype_dyn
- dynamic
- dynamic_dyn
- filters
- filters_dyn
- go_backwards
- inbound_nodes
- inbound_nodes_dyn
- input
- input_dyn
- input_mask
- input_mask_dyn
- input_shape
- input_shape_dyn
- input_spec
- input_spec_dyn
- kernel_constraint
- kernel_constraint_dyn
- kernel_initializer
- kernel_initializer_dyn
- kernel_regularizer
- kernel_regularizer_dyn
- kernel_size
- kernel_size_dyn
- losses
- losses_dyn
- metrics
- metrics_dyn
- name
- name_dyn
- name_scope
- name_scope_dyn
- non_trainable_variables
- non_trainable_variables_dyn
- non_trainable_weights
- non_trainable_weights_dyn
- outbound_nodes
- outbound_nodes_dyn
- output
- output_dyn
- output_mask
- output_mask_dyn
- output_shape
- output_shape_dyn
- padding
- padding_dyn
- PythonObject
- recurrent_activation
- recurrent_activation_dyn
- recurrent_constraint
- recurrent_constraint_dyn
- recurrent_dropout
- recurrent_dropout_dyn
- recurrent_initializer
- recurrent_initializer_dyn
- recurrent_regularizer
- recurrent_regularizer_dyn
- return_sequences
- return_state
- state_spec
- stateful
- states
- states_dyn
- strides
- strides_dyn
- submodules
- submodules_dyn
- supports_masking
- time_major
- trainable
- trainable_dyn
- trainable_variables
- trainable_variables_dyn
- trainable_weights
- trainable_weights_dyn
- unit_forget_bias
- unit_forget_bias_dyn
- unroll
- updates
- updates_dyn
- use_bias
- use_bias_dyn
- variables
- variables_dyn
- weights
- weights_dyn
- zero_output_for_mask
Public instance methods
object __call__(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> initial_state, IDictionary<string, object> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> initial_state, object constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> initial_state, string constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, object initial_state, IDictionary<string, object> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, object initial_state, IEnumerable<IGraphNodeBase> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, object initial_state, IGraphNodeBase constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, object initial_state, object constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, object initial_state, string constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> initial_state, IDictionary<string, object> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> initial_state, IEnumerable<IGraphNodeBase> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> initial_state, IGraphNodeBase constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> initial_state, object constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> initial_state, string constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, object initial_state, IDictionary<string, object> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, object initial_state, IEnumerable<IGraphNodeBase> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, object initial_state, IGraphNodeBase constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, object initial_state, object constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IGraphNodeBase inputs, object initial_state, string constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> initial_state, IGraphNodeBase constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call__(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> initial_state, IEnumerable<IGraphNodeBase> constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
object __call___dyn(object inputs, object initial_state, object constants, IDictionary<string, object> kwargs)
`Bidirectional.__call__` implements the same API as the wrapped `RNN`.
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, IGraphNodeBase training, object initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, IGraphNodeBase training, PythonClassContainer initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, bool training, object initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, object initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, bool training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, bool training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, bool training, PythonClassContainer initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, bool training, object initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, PythonClassContainer initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, bool training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, object initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, bool training, PythonClassContainer initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, bool training, object initial_state)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, bool training, PythonClassContainer initial_state)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, object initial_state)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, PythonClassContainer initial_state)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, bool training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, bool training, object initial_state)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, bool training, PythonClassContainer initial_state)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, bool training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, bool training, PythonClassContainer initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, IGraphNodeBase training, object initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, bool training, object initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, bool training, PythonClassContainer initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, bool training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, object initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, PythonClassContainer initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, bool training, object initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> mask, bool training, PythonClassContainer initial_state)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, IGraphNodeBase training, PythonClassContainer initial_state)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, PythonClassContainer initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, bool training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, IGraphNodeBase training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, bool training, object initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, bool training, PythonClassContainer initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> mask, bool training, IEnumerable<IGraphNodeBase> initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, IGraphNodeBase training, object initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, bool training, object initial_state, object constants)
Tensor call(IEnumerable<IGraphNodeBase> inputs, IGraphNodeBase mask, IGraphNodeBase training, PythonClassContainer initial_state, object constants)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, IGraphNodeBase training, object initial_state)
Tensor call(IGraphNodeBase inputs, IGraphNodeBase mask, IGraphNodeBase training, PythonClassContainer initial_state)
object call_dyn(object inputs, object mask, object training, object initial_state, object constants)
object call_dyn(object inputs, object mask, object training, object initial_state)
object compute_output_shape(PythonClassContainer input_shape)
object compute_output_shape(ValueTuple<object, int> input_shape)
object compute_output_shape(IEnumerable<Nullable<int>> input_shape)
object get_initial_state(IEnumerable<object> inputs)
object get_initial_state(IGraphNodeBase inputs)
object get_initial_state_dyn(object inputs)
void reset_states(IEnumerable<ndarray> states)
void reset_states(ndarray states)
void reset_states(PythonClassContainer states)
object reset_states_dyn(object states)
Public static methods
ConvLSTM2D NewDyn(object filters, object kernel_size, ImplicitContainer<T> strides, ImplicitContainer<T> padding, object data_format, ImplicitContainer<T> dilation_rate, ImplicitContainer<T> activation, ImplicitContainer<T> recurrent_activation, ImplicitContainer<T> use_bias, ImplicitContainer<T> kernel_initializer, ImplicitContainer<T> recurrent_initializer, ImplicitContainer<T> bias_initializer, ImplicitContainer<T> unit_forget_bias, object kernel_regularizer, object recurrent_regularizer, object bias_regularizer, object activity_regularizer, object kernel_constraint, object recurrent_constraint, object bias_constraint, ImplicitContainer<T> return_sequences, ImplicitContainer<T> go_backwards, ImplicitContainer<T> stateful, ImplicitContainer<T> dropout, ImplicitContainer<T> recurrent_dropout, IDictionary<string, object> kwargs)
Public properties
object activation get;
object activation_dyn get;
object activity_regularizer get; set;
Optional regularizer function for the output of this layer.