from keras.layers import Bidirectional, Concatenate, Permute, Dot, Input, LSTM, Multiply
from keras.layers import RepeatVector, Dense, Activation, Lambda
from keras.optimizers import Adam
from keras.utils import to_categorical
from keras.models import load_model, Model
import keras.backend as K
import numpy as np
from faker import Faker
import random
from tqdm import tqdm
from babel.dates import format_date
from nmt_utils import *
import matplotlib.pyplot as plt
%matplotlib inline
m = 10000
dataset, human_vocab, machine_vocab, inv_machine_vocab = load_dataset(m)
dataset[:10]
[('9 may 1998', '1998-05-09'),
('10.09.70', '1970-09-10'),
('4/28/90', '1990-04-28'),
('thursday january 26 1995', '1995-01-26'),
('monday march 7 1983', '1983-03-07'),
('sunday may 22 1988', '1988-05-22'),
('tuesday july 8 2008', '2008-07-08'),
('08 sep 1999', '1999-09-08'),
('1 jan 1981', '1981-01-01'),
('monday may 22 1995', '1995-05-22')]
Tx = 30
Ty = 10
X, Y, Xoh, Yoh = preprocess_data(dataset, human_vocab, machine_vocab, Tx, Ty)
print("X.shape:", X.shape)
print("Y.shape:", Y.shape)
print("Xoh.shape:", Xoh.shape)
print("Yoh.shape:", Yoh.shape)
X.shape: (10000, 30)
Y.shape: (10000, 10)
Xoh.shape: (10000, 30, 37)
Yoh.shape: (10000, 10, 11)
index = 0
print("Source date:", dataset[index][0])
print("Target date:", dataset[index][1])
print()
print("Source after preprocessing (indices):", X[index])
print("Target after preprocessing (indices):", Y[index])
print()
print("Source after preprocessing (one-hot):", Xoh[index])
print("Target after preprocessing (one-hot):", Yoh[index])
# Defined shared layers as global variables
repeator = RepeatVector(Tx)
concatenator = Concatenate(axis=-1)
densor1 = Dense(10, activation = "tanh")
densor2 = Dense(1, activation = "relu")
activator = Activation(softmax, name='attention_weights') # We are using a custom softmax(axis = 1) loaded in this notebook
dotor = Dot(axes = 1)
# GRADED FUNCTION: one_step_attention
def one_step_attention(a, s_prev):
"""
Performs one step of attention: Outputs a context vector computed as a dot product of the attention weights
"alphas" and the hidden states "a" of the Bi-LSTM.
Arguments:
a -- hidden state output of the Bi-LSTM, numpy-array of shape (m, Tx, 2*n_a)
s_prev -- previous hidden state of the (post-attention) LSTM, numpy-array of shape (m, n_s)
Returns:
context -- context vector, input of the next (post-attetion) LSTM cell
"""
### START CODE HERE ###
# Use repeator to repeat s_prev to be of shape (m, Tx, n_s) so that you can concatenate it with all hidden states "a" (≈ 1 line)
s_prev = repeator(s_prev)
# Use concatenator to concatenate a and s_prev on the last axis (≈ 1 line)
concat = concatenator([a, s_prev])
# Use densor1 to propagate concat through a small fully-connected neural network to compute the "intermediate energies" variable e. (≈1 lines)
e = densor1(concat)
# Use densor2 to propagate e through a small fully-connected neural network to compute the "energies" variable energies. (≈1 lines)
energies = densor2(e)
# Use "activator" on "energies" to compute the attention weights "alphas" (≈ 1 line)
alphas = activator(energies)
# Use dotor together with "alphas" and "a" to compute the context vector to be given to the next (post-attention) LSTM-cell (≈ 1 line)
context = dotor([alphas, a])
### END CODE HERE ###
return context
n_a = 32
n_s = 64
post_activation_LSTM_cell = LSTM(n_s, return_state = True)
output_layer = Dense(len(machine_vocab), activation=softmax)
# GRADED FUNCTION: model
def model(Tx, Ty, n_a, n_s, human_vocab_size, machine_vocab_size):
"""
Arguments:
Tx -- length of the input sequence
Ty -- length of the output sequence
n_a -- hidden state size of the Bi-LSTM
n_s -- hidden state size of the post-attention LSTM
human_vocab_size -- size of the python dictionary "human_vocab"
machine_vocab_size -- size of the python dictionary "machine_vocab"
Returns:
model -- Keras model instance
"""
# Define the inputs of your model with a shape (Tx,)
# Define s0 and c0, initial hidden state for the decoder LSTM of shape (n_s,)
X = Input(shape=(Tx, human_vocab_size))
s0 = Input(shape=(n_s,), name='s0')
c0 = Input(shape=(n_s,), name='c0')
s = s0
c = c0
# Initialize empty list of outputs
outputs = []
### START CODE HERE ###
# Step 1: Define your pre-attention Bi-LSTM. Remember to use return_sequences=True. (≈ 1 line)
a = Bidirectional(LSTM(n_a, return_sequences=True))(X)
# Step 2: Iterate for Ty steps
for t in range(Ty):
# Step 2.A: Perform one step of the attention mechanism to get back the context vector at step t (≈ 1 line)
context = one_step_attention(a, s)
# Step 2.B: Apply the post-attention LSTM cell to the "context" vector.
# Don't forget to pass: initial_state = [hidden state, cell state] (≈ 1 line)
s, _, c = post_activation_LSTM_cell(context, initial_state=[s, c])
# Step 2.C: Apply Dense layer to the hidden state output of the post-attention LSTM (≈ 1 line)
out = output_layer(s)
# Step 2.D: Append "out" to the "outputs" list (≈ 1 line)
outputs.append(out)
# Step 3: Create model instance taking three inputs and returning the list of outputs. (≈ 1 line)
model = Model(inputs=[X, s0, c0], outputs=outputs)
### END CODE HERE ###
return model
model = model(Tx, Ty, n_a, n_s, len(human_vocab), len(machine_vocab))
model.summary()
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) (None, 30, 37) 0
__________________________________________________________________________________________________
s0 (InputLayer) (None, 64) 0
__________________________________________________________________________________________________
bidirectional_1 (Bidirectional) (None, 30, 64) 17920 input_1[0][0]
__________________________________________________________________________________________________
repeat_vector_1 (RepeatVector) (None, 30, 64) 0 s0[0][0]
lstm_1[0][0]
lstm_1[1][0]
lstm_1[2][0]
lstm_1[3][0]
lstm_1[4][0]
lstm_1[5][0]
lstm_1[6][0]
lstm_1[7][0]
lstm_1[8][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 30, 128) 0 bidirectional_1[0][0]
repeat_vector_1[0][0]
bidirectional_1[0][0]
repeat_vector_1[1][0]
bidirectional_1[0][0]
repeat_vector_1[2][0]
bidirectional_1[0][0]
repeat_vector_1[3][0]
bidirectional_1[0][0]
repeat_vector_1[4][0]
bidirectional_1[0][0]
repeat_vector_1[5][0]
bidirectional_1[0][0]
repeat_vector_1[6][0]
bidirectional_1[0][0]
repeat_vector_1[7][0]
bidirectional_1[0][0]
repeat_vector_1[8][0]
bidirectional_1[0][0]
repeat_vector_1[9][0]
__________________________________________________________________________________________________
dense_1 (Dense) (None, 30, 10) 1290 concatenate_1[0][0]
concatenate_1[1][0]
concatenate_1[2][0]
concatenate_1[3][0]
concatenate_1[4][0]
concatenate_1[5][0]
concatenate_1[6][0]
concatenate_1[7][0]
concatenate_1[8][0]
concatenate_1[9][0]
__________________________________________________________________________________________________
dense_2 (Dense) (None, 30, 1) 11 dense_1[0][0]
dense_1[1][0]
dense_1[2][0]
dense_1[3][0]
dense_1[4][0]
dense_1[5][0]
dense_1[6][0]
dense_1[7][0]
dense_1[8][0]
dense_1[9][0]
__________________________________________________________________________________________________
attention_weights (Activation) (None, 30, 1) 0 dense_2[0][0]
dense_2[1][0]
dense_2[2][0]
dense_2[3][0]
dense_2[4][0]
dense_2[5][0]
dense_2[6][0]
dense_2[7][0]
dense_2[8][0]
dense_2[9][0]
__________________________________________________________________________________________________
dot_1 (Dot) (None, 1, 64) 0 attention_weights[0][0]
bidirectional_1[0][0]
attention_weights[1][0]
bidirectional_1[0][0]
attention_weights[2][0]
bidirectional_1[0][0]
attention_weights[3][0]
bidirectional_1[0][0]
attention_weights[4][0]
bidirectional_1[0][0]
attention_weights[5][0]
bidirectional_1[0][0]
attention_weights[6][0]
bidirectional_1[0][0]
attention_weights[7][0]
bidirectional_1[0][0]
attention_weights[8][0]
bidirectional_1[0][0]
attention_weights[9][0]
bidirectional_1[0][0]
__________________________________________________________________________________________________
c0 (InputLayer) (None, 64) 0
__________________________________________________________________________________________________
lstm_1 (LSTM) [(None, 64), (None, 33024 dot_1[0][0]
s0[0][0]
c0[0][0]
dot_1[1][0]
lstm_1[0][0]
lstm_1[0][2]
dot_1[2][0]
lstm_1[1][0]
lstm_1[1][2]
dot_1[3][0]
lstm_1[2][0]
lstm_1[2][2]
dot_1[4][0]
lstm_1[3][0]
lstm_1[3][2]
dot_1[5][0]
lstm_1[4][0]
lstm_1[4][2]
dot_1[6][0]
lstm_1[5][0]
lstm_1[5][2]
dot_1[7][0]
lstm_1[6][0]
lstm_1[6][2]
dot_1[8][0]
lstm_1[7][0]
lstm_1[7][2]
dot_1[9][0]
lstm_1[8][0]
lstm_1[8][2]
__________________________________________________________________________________________________
dense_3 (Dense) (None, 11) 715 lstm_1[0][0]
lstm_1[1][0]
lstm_1[2][0]
lstm_1[3][0]
lstm_1[4][0]
lstm_1[5][0]
lstm_1[6][0]
lstm_1[7][0]
lstm_1[8][0]
lstm_1[9][0]
==================================================================================================
Total params: 52,960
Trainable params: 52,960
Non-trainable params: 0
### START CODE HERE ### (≈2 lines)
opt = Adam(lr=0.005, decay=0.01)
model.compile(optimizer=opt,
loss='categorical_crossentropy',
metrics=['accuracy'])
### END CODE HERE ###
s0 = np.zeros((m, n_s))
c0 = np.zeros((m, n_s))
outputs = list(Yoh.swapaxes(0,1))
model.fit([Xoh, s0, c0], outputs, epochs=1, batch_size=100)
Epoch 1/1
10000/10000 [==============================] - 11s 1ms/step - loss: 16.3522 - dense_3_loss: 2.5974 - dense_3_acc: 0.5065 - dense_3_acc_1: 0.6418 - dense_3_acc_2: 0.2782 - dense_3_acc_3: 0.0636 - dense_3_acc_4: 0.9898 - dense_3_acc_5: 0.3664 - dense_3_acc_6: 0.0582 - dense_3_acc_7: 0.9735 - dense_3_acc_8: 0.2067 - dense_3_acc_9: 0.0928
model.load_weights('models/model.h5')
EXAMPLES = ['3 May 1979', '5 April 09', '21th of August 2016', 'Tue 10 Jul 2007', 'Saturday May 9 2018', 'March 3 2001', 'March 3rd 2001', '1 March 2001']
for example in EXAMPLES:
source = string_to_int(example, Tx, human_vocab)
# source = np.array(list(map(lambda x: to_categorical(x, num_classes=len(human_vocab)), source))).swapaxes(0,1)
# prediction = model.predict([source, s0, c0])
source = np.array(list(map(lambda x: to_categorical(x, num_classes=len(human_vocab)), source))) #不能变换 数据维度 ，
ttt=np.expand_dims(source,axis=0) # 在 axis=0的位置 ，增加一个 维度，以适应 输入维度要求
prediction = model.predict([ttt, s0, c0])
prediction = np.argmax(prediction, axis = -1)
output = [inv_machine_vocab[int(i)] for i in prediction]
print("source:", example)
print("output:", ''.join(output))
source: 3 May 1979
output: 1979-05-03
source: 5 April 09
output: 2009-05-05
source: 21th of August 2016
output: 2016-08-21
source: Tue 10 Jul 2007
output: 2007-07-10
source: Saturday May 9 2018
output: 2018-05-09
source: March 3 2001
output: 2001-03-03
source: March 3rd 2001
output: 2001-03-03
source: 1 March 2001
output: 2001-03-01
model.summary()
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) (None, 30, 37) 0
__________________________________________________________________________________________________
s0 (InputLayer) (None, 64) 0
__________________________________________________________________________________________________
bidirectional_1 (Bidirectional) (None, 30, 64) 17920 input_1[0][0]
__________________________________________________________________________________________________
repeat_vector_1 (RepeatVector) (None, 30, 64) 0 s0[0][0]
lstm_1[0][0]
lstm_1[1][0]
lstm_1[2][0]
lstm_1[3][0]
lstm_1[4][0]
lstm_1[5][0]
lstm_1[6][0]
lstm_1[7][0]
lstm_1[8][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 30, 128) 0 bidirectional_1[0][0]
repeat_vector_1[0][0]
bidirectional_1[0][0]
repeat_vector_1[1][0]
bidirectional_1[0][0]
repeat_vector_1[2][0]
bidirectional_1[0][0]
repeat_vector_1[3][0]
bidirectional_1[0][0]
repeat_vector_1[4][0]
bidirectional_1[0][0]
repeat_vector_1[5][0]
bidirectional_1[0][0]
repeat_vector_1[6][0]
bidirectional_1[0][0]
repeat_vector_1[7][0]
bidirectional_1[0][0]
repeat_vector_1[8][0]
bidirectional_1[0][0]
repeat_vector_1[9][0]
__________________________________________________________________________________________________
dense_1 (Dense) (None, 30, 10) 1290 concatenate_1[0][0]
concatenate_1[1][0]
concatenate_1[2][0]
concatenate_1[3][0]
concatenate_1[4][0]
concatenate_1[5][0]
concatenate_1[6][0]
concatenate_1[7][0]
concatenate_1[8][0]
concatenate_1[9][0]
__________________________________________________________________________________________________
dense_2 (Dense) (None, 30, 1) 11 dense_1[0][0]
dense_1[1][0]
dense_1[2][0]
dense_1[3][0]
dense_1[4][0]
dense_1[5][0]
dense_1[6][0]
dense_1[7][0]
dense_1[8][0]
dense_1[9][0]
__________________________________________________________________________________________________
attention_weights (Activation) (None, 30, 1) 0 dense_2[0][0]
dense_2[1][0]
dense_2[2][0]
dense_2[3][0]
dense_2[4][0]
dense_2[5][0]
dense_2[6][0]
dense_2[7][0]
dense_2[8][0]
dense_2[9][0]
__________________________________________________________________________________________________
dot_1 (Dot) (None, 1, 64) 0 attention_weights[0][0]
bidirectional_1[0][0]
attention_weights[1][0]
bidirectional_1[0][0]
attention_weights[2][0]
bidirectional_1[0][0]
attention_weights[3][0]
bidirectional_1[0][0]
attention_weights[4][0]
bidirectional_1[0][0]
attention_weights[5][0]
bidirectional_1[0][0]
attention_weights[6][0]
bidirectional_1[0][0]
attention_weights[7][0]
bidirectional_1[0][0]
attention_weights[8][0]
bidirectional_1[0][0]
attention_weights[9][0]
bidirectional_1[0][0]
__________________________________________________________________________________________________
c0 (InputLayer) (None, 64) 0
__________________________________________________________________________________________________
lstm_1 (LSTM) [(None, 64), (None, 33024 dot_1[0][0]
s0[0][0]
c0[0][0]
dot_1[1][0]
lstm_1[0][0]
lstm_1[0][2]
dot_1[2][0]
lstm_1[1][0]
lstm_1[1][2]
dot_1[3][0]
lstm_1[2][0]
lstm_1[2][2]
dot_1[4][0]
lstm_1[3][0]
lstm_1[3][2]
dot_1[5][0]
lstm_1[4][0]
lstm_1[4][2]
dot_1[6][0]
lstm_1[5][0]
lstm_1[5][2]
dot_1[7][0]
lstm_1[6][0]
lstm_1[6][2]
dot_1[8][0]
lstm_1[7][0]
lstm_1[7][2]
dot_1[9][0]
lstm_1[8][0]
lstm_1[8][2]
__________________________________________________________________________________________________
dense_3 (Dense) (None, 11) 715 lstm_1[0][0]
lstm_1[1][0]
lstm_1[2][0]
lstm_1[3][0]
lstm_1[4][0]
lstm_1[5][0]
lstm_1[6][0]
lstm_1[7][0]
lstm_1[8][0]
lstm_1[9][0]
==================================================================================================
Total params: 52,960
Trainable params: 52,960
Non-trainable params: 0
attention_map = plot_attention_map(model, human_vocab, inv_machine_vocab, "Tuesday 09 Oct 1993", num = 7, n_s = 64)
