Initialize the hidden state of an LSTM/GRU
:param batch_size: The batch_size of the hidden state
:return: hidden state of dims (n_layers, batch_size, hidden_dim)
'''
# Implement function
weight = next(self.parameters()).data
# initialize hidden state with zero weights, and move to GPU if available
if (train_on_gpu):
hidden = (weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().cuda(),
weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().cuda())
else:
hidden = (weight.new(self.n_layers, batch_size, self.hidden_dim).zero_(),
weight.new(self.n_layers, batch_size, self.hidden_dim).zero_())
return hidden
tests.test_rnn(RNN, train_on_gpu)
def forward_back_prop(rnn, optimizer, criterion, inp, target, hidden):
"""
Forward and backward propagation on the neural network
:param rnn: The PyTorch Module that holds the neural network
:param optimizer: The PyTorch optimizer for the neural network
:param criterion: The PyTorch loss function
:param inp: A batch of input to the neural network
:param target: The target output for the batch of input
:return: The loss and the latest hidden state Tensor
"""
if (train_on_gpu):
inp, target = inp.cuda(), target.cuda()
# move data to GPU, if available
# perform backpropagation and optimization
def test_rnn_structure(self):
problem_unittests.test_rnn(RNN=lost_episode.RNN,
train_on_gpu=self.train_on_gpu)
def run_tests():
tests.test_rnn(RNN, train_on_gpu)
tests.test_forward_back_prop(RNN, forward_back_prop, train_on_gpu)
'''
Initialize the hidden state of an LSTM/GRU
:param batch_size: The batch_size of the hidden state
:return: hidden state of dims (n_layers, batch_size, hidden_dim)
'''
# Implement function
# initialize hidden state with zero weights, and move to GPU if available
# Create two new tensors with sizes n_layers x batch_size x n_hidden,
# initialized to zero, for hidden state and cell state of LSTM
weight = next(self.parameters()).data
if (train_on_gpu):
hidden = (weight.new(self.n_layers, batch_size,
self.hidden_dim).zero_().cuda(),
weight.new(self.n_layers, batch_size,
self.hidden_dim).zero_().cuda())
else:
hidden = (weight.new(self.n_layers, batch_size,
self.hidden_dim).zero_(),
weight.new(self.n_layers, batch_size,
self.hidden_dim).zero_())
return hidden
from problem_unittests import test_rnn
test_rnn(RNN, False)
