Type Conv1D
Namespace tensorflow.keras.layers
Parent Conv
Interfaces IConv1D
1D convolution layer (e.g. temporal convolution). This layer creates a convolution kernel that is convolved
with the layer input over a single spatial (or temporal) dimension
to produce a tensor of outputs.
If `use_bias` is True, a bias vector is created and added to the outputs.
Finally, if `activation` is not `None`,
it is applied to the outputs as well. When using this layer as the first layer in a model,
provide an `input_shape` argument
(tuple of integers or `None`, e.g.
`(10, 128)` for sequences of 10 vectors of 128-dimensional vectors,
or `(None, 128)` for variable-length sequences of 128-dimensional vectors.
Methods
Properties
- activation
- activity_regularizer
- activity_regularizer_dyn
- bias
- bias_constraint
- bias_initializer
- bias_regularizer
- built
- data_format
- dilation_rate
- dtype
- dtype_dyn
- dynamic
- dynamic_dyn
- filters
- inbound_nodes
- inbound_nodes_dyn
- input
- input_dyn
- input_mask
- input_mask_dyn
- input_shape
- input_shape_dyn
- input_spec
- input_spec_dyn
- kernel
- kernel_constraint
- kernel_initializer
- kernel_regularizer
- kernel_size
- 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
- PythonObject
- rank
- stateful
- strides
- submodules
- submodules_dyn
- supports_masking
- trainable
- trainable_dyn
- trainable_variables
- trainable_variables_dyn
- trainable_weights
- trainable_weights_dyn
- updates
- updates_dyn
- use_bias
- variables
- variables_dyn
- weights
- weights_dyn