Created
August 30, 2018 09:25
-
-
Save n-Guard/cedd69b50803c82f6ce437ea771a620c to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
from keras.layers import Dense, Dropout, Activation, Flatten | |
from keras.layers import Conv1D, Conv2D, MaxPooling2D, MaxPooling1D, AveragePooling2D, GRU | |
from keras.layers import TimeDistributed, Bidirectional | |
from keras.layers.recurrent import LSTM | |
from keras.models import Sequential | |
def sigmoid(z): | |
s = 1.0 / (1.0 + np.exp(-1.0 * z)) | |
return s | |
def relu(z): | |
z[z < 0] = 0 | |
return z | |
def lstm_impl(input, units, W, U, b, activation, recurrent_activation): | |
h_tm1 = np.zeros((1, units), dtype=np.float32) # previous memory state | |
c_tm1 = np.zeros((1, units), dtype=np.float32) # previous carry state | |
# allocation | |
result = np.zeros(input.shape[:-1] + (units,), dtype=np.float32) | |
X = np.dot(input, W) + b | |
x_i = X[:, :, :units] | |
x_f = X[:, :, units: units * 2] | |
x_c = X[:, :, units * 2: units * 3] | |
x_o = X[:, :, units * 3:] | |
for k in range(input.shape[1]): | |
ifco = np.dot(h_tm1, U) | |
i = recurrent_activation(x_i[:,k,:] + ifco[:,:units]) | |
f = recurrent_activation(x_f[:,k,:] + ifco[:,units: units * 2]) | |
c = f * c_tm1 + i * activation(x_c[:,k,:] + ifco[:,units * 2: units * 3]) | |
o = recurrent_activation(x_o[:,k,:] + ifco[:,units * 3:]) | |
h = o * activation(c) | |
c_tm1 = c[:] | |
h_tm1 = h[:] | |
result[:,k,:] = h[np.newaxis,:,:] | |
return result | |
if __name__ == "__main__": | |
lstm_model = Sequential() | |
input_shape = (2,2) | |
activation = np.tanh | |
recurrent_activation = sigmoid | |
# input layer | |
np.random.seed(7) | |
lstm_model.add(LSTM(units=2, input_shape=input_shape, activation='tanh', recurrent_activation='sigmoid', | |
return_sequences=True)) | |
# output layer | |
lstm_model.compile(optimizer='adam', loss='binary_crossentropy') | |
lstm_model.summary() | |
input = np.ones((1,2,2)) | |
result1 = lstm_model.predict(input) | |
units = int(int(lstm_model.layers[0].trainable_weights[0].shape[1]) / 4) | |
print("Number of units: ", units) | |
W = lstm_model.layers[0].get_weights()[0] | |
U = lstm_model.layers[0].get_weights()[1] | |
b = lstm_model.layers[0].get_weights()[2] | |
result2 = lstm_impl(input, units, W, U, b, activation, recurrent_activation) | |
print('Result all_close: ' + str(np.allclose(result1, result2, rtol=1e-06))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment