def forward(self, inputs, weights):
x, lstm_state = inputs
# LSTM state consists of c and h.
c, h = np.split(lstm_state, 2, axis=-1)
# Dense layer on the concatenation of x and h.
w, b = weights
y = np.dot(np.concatenate([x, h], axis=-1), w) + b
# i = input_gate, j = new_input, f = forget_gate, o = output_gate
i, j, f, o = np.split(y, 4, axis=-1)
new_c = c * backend.sigmoid(f) + backend.sigmoid(i) * np.tanh(j)
new_h = np.tanh(new_c) * backend.sigmoid(o)
return new_h, np.concatenate([new_c, new_h], axis=-1)
def forward(self, inputs, weights):
x, gru_state = inputs
# Dense layer on the concatenation of x and h.
w1, b1, w2, b2 = weights
y = np.dot(np.concatenate([x, gru_state], axis=-1), w1) + b1
# Update and reset gates.
u, r = np.split(backend.sigmoid(y), 2, axis=-1)
# Candidate.
c = np.dot(np.concatenate([x, r * gru_state], axis=-1), w2) + b2
new_gru_state = u * gru_state + (1 - u) * np.tanh(c)
return new_gru_state, new_gru_state
def Tanh(x, **unused_kwargs): return np.tanh(x)
def FastGelu(x, **unused_kwargs): return 0.5 * x * (1 + np.tanh(x * 0.7978845608 * (1 + 0.044715 * x * x)))