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