def forward(self, X, mode):
h = np.zeros(self.hshape) # init hidden state
for t in xrange(self.num_unroll_steps):
h = layers.rnn_step(X, h, self.params['Wx'],
self.params['Wh'], self.params['b'])
y = layers.affine(h, self.params['Wa'], self.params['ba'])
return y
def forward(self, X, mode):
h = np.zeros(self.hshape) # init hidden state
for t in range(self.num_unroll_steps):
h = layers.rnn_step(X, h, self.params['Wx'], self.params['Wh'],
self.params['b'])
y = layers.affine(h, self.params['Wa'], self.params['ba'])
return y
def forward(self, X, mode):
seq_len = X.shape[1]
h = self.params['h0']
for t in xrange(seq_len):
h = layers.rnn_step(X[:, t, :], h, self.params['Wx'],
self.params['Wh'], self.params['b'])
y = layers.affine(h, self.params['Wa'], self.params['ba'])
return y
def forward(self, X, mode):
seq_len = X.shape[1]
h = self.params['h0']
for t in xrange(seq_len):
h = layers.rnn_step(X[:, t, :], h, self.params['Wx'],
self.params['Wh'], self.params['b'])
y = layers.affine(h, self.params['Wa'], self.params['ba'])
return y
def step(self, x, h, *args, **kwargs):
"""
Abstract step function for rnn
:param x: current input, batched matrix
:param h: previous output
:return: output
"""
return layers.rnn_step(x, h, self.params('Wx'), self.params('Wh'),
self.params('b'))
def forward(self, X, mode):
seq_len = X.shape[1]
batch_size = X.shape[0]
hidden_size = self.params['Wh'].shape[0]
h = np.zeros((batch_size, hidden_size))
for t in xrange(seq_len):
h = layers.rnn_step(X[:, t, :], h, self.params['Wx'],
self.params['Wh'], self.params['b'])
y = layers.affine(h, self.params['Wa'], self.params['ba'])
return y
