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

Public Attributes

 attention_type
 
- Public Attributes inherited from rnn_cell.LSTMWithAttentionCell
 encoder_output_dim
 
 encoder_outputs
 
 decoder_input_dim
 
 decoder_state_dim
 
 weighted_encoder_outputs
 
 encoder_outputs_transposed
 
 attention_type
 
 lstm_memory_optimization
 
 attention_memory_optimization
 
- Public Attributes inherited from rnn_cell.RNNCell
 name
 
 recompute_blobs
 

Additional Inherited Members

- Public Member Functions inherited from rnn_cell.LSTMWithAttentionCell
def __init__ (self, encoder_output_dim, encoder_outputs, decoder_input_dim, decoder_state_dim, name, attention_type, weighted_encoder_outputs, forget_bias, lstm_memory_optimization, attention_memory_optimization)
 
def get_attention_weights (self)
 
def prepare_input (self, model, input_blob)
 
def get_state_names (self)
 
def get_outputs_with_grads (self)
 
def get_output_size (self)
 
- Public Member Functions inherited from rnn_cell.RNNCell
def __init__ (self, name)
 
def scope (self, name)
 
def apply_over_sequence (self, model, inputs, seq_lengths, initial_states, outputs_with_grads=None)
 
def apply (self, model, input_t, seq_lengths, states, timestep)
 
def prepare_input (self, model, input_blob)
 
def get_state_names (self)
 

Detailed Description

Definition at line 837 of file rnn_cell.py.


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