Caffe2 - Python API
A deep learning, cross platform ML framework
Public Member Functions | Public Attributes | List of all members
caffe2.python.rnn_cell.DropoutCell Class Reference
Inheritance diagram for caffe2.python.rnn_cell.DropoutCell:
caffe2.python.rnn_cell.RNNCell

Public Member Functions

def __init__ (self, internal_cell, dropout_ratio=None, use_cudnn=False, kwargs)
 
- Public Member Functions inherited from caffe2.python.rnn_cell.RNNCell
def __init__ (self, name=None, forward_only=False, initializer=None)
 
def initializer (self)
 
def initializer (self, value)
 
def scope (self, name)
 
def apply_over_sequence (self, model, inputs, seq_lengths=None, initial_states=None, outputs_with_grads=None)
 
def apply (self, model, input_t, seq_lengths, states, timestep)
 
def apply_override (self, model, input_t, seq_lengths, timestep, extra_inputs=None)
 
def prepare_input (self, model, input_blob)
 
def get_output_state_index (self)
 
def get_state_names (self)
 
def get_state_names_override (self)
 
def get_output_dim (self)
 

Public Attributes

 internal_cell
 
 dropout_ratio
 
 is_test
 
 use_cudnn
 
 prepare_input
 
 get_output_state_index
 
 get_state_names
 
 get_output_dim
 
 mask
 
- Public Attributes inherited from caffe2.python.rnn_cell.RNNCell
 name
 
 recompute_blobs
 
 forward_only
 

Detailed Description

Wraps arbitrary RNNCell, applying dropout to its output (but not to the
recurrent connection for the corresponding state).

Definition at line 816 of file rnn_cell.py.


The documentation for this class was generated from the following file: