View source on GitHub
|
Sample Keras Value Network with LSTM cells .
Implements a network that will generate the following layers:
[optional]: preprocessing_layers # preprocessing_layers [optional]: (Add | Concat(axis=-1) | ...) # preprocessing_combiner [optional]: Conv2D # conv_layer_params Flatten [optional]: Dense # input_fc_layer_params [optional]: LSTM # lstm_cell_params [optional]: Dense # output_fc_layer_params Dense -> 1 # Value output
Classes
class ValueRnnNetwork: Recurrent value network. Reduces to 1 value output per batch item.
Other Members | |
|---|---|
| absolute_import |
Instance of __future__._Feature
|
| division |
Instance of __future__._Feature
|
| print_function |
Instance of __future__._Feature
|