Caffe2 - Python API
A deep learning, cross platform ML framework
Public Member Functions | Public Attributes | List of all members
torch.nn.modules.rnn.RNNBase Class Reference
Inheritance diagram for torch.nn.modules.rnn.RNNBase:
torch.nn.modules.rnn.GRU torch.nn.modules.rnn.LSTM torch.nn.modules.rnn.RNN

Public Member Functions

def __init__ (self, mode, input_size, hidden_size, num_layers=1, bias=True, batch_first=False, dropout=0., bidirectional=False)
def flatten_parameters (self)
def reset_parameters (self)
def get_flat_weights (self)
def check_input (self, input, batch_sizes)
def get_expected_hidden_size (self, input, batch_sizes)
def check_hidden_size (self, hx, expected_hidden_size, msg='Expected hidden size{}, got)
def check_forward_args (self, input, hidden, batch_sizes)
def permute_hidden (self, hx, permutation)
def forward (self, input, hx=None)
def extra_repr (self)
def __setstate__ (self, d)
def all_weights (self)

Public Attributes


Detailed Description

Definition at line 28 of file

Member Function Documentation

def torch.nn.modules.rnn.RNNBase.flatten_parameters (   self)
Resets parameter data pointer so that they can use faster code paths.

Right now, this works only if the module is on the GPU and cuDNN is enabled.
Otherwise, it's a no-op.

Definition at line 94 of file

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