import numpy as np
from keras.models import Model
from keras.models import load_model
from keras.layers import Input,LSTM,Dense
batch_size = 64  # Batch size for training.
epochs = 100  # Number of epochs to train for.
latent_dim = 256  # Latent dimensionality of the encoding space.
num_samples = 10000  #
 
 Number of samples to train on.
# Path to the data txt file on disk.
data_path = 'fra.txt'

input_texts = []
target_texts = []
input_characters = set()
target_characters = set()
lines = open(data_path,encoding='utf-8').read().split('\n')
for index,line in enumerate(lines[: min(num_samples, len(lines) - 1)]):
    input_text, target_text 
 
= line.split('\t')
    target_text = '\t' + target_text + '\n'
    input_texts.append(input_text)
    target_texts.append(target_text)
    for char in input_text:
        if char not in input_characters:
            input_characters.add(char)
    for char in target_text:
        if char not in target_characters:
            target_characters.add(char)
input_characters 
 
= sorted(list(input_characters))
target_characters = sorted(list(target_characters))
# 統計source和target的字元數
num_encoder_tokens = len(input_characters)
num_decoder_tokens = len(target_characters)
# 取出最長的句子的長度
max_encoder_seq_length = max([len(txt) for txt in input_texts])
max_decoder_seq_length = max([len(txt) for txt in target_texts])
# 列印具體的資訊
print('Number of samples:', len(input_texts))
print('Number of unique input tokens:', num_encoder_tokens)
print('Number of unique output tokens:', num_decoder_tokens)
print('Max sequence length for inputs:', max_encoder_seq_length)
print('Max sequence length for outputs:', max_decoder_seq_length)
# 將它們轉化為id的形式儲存（char-to-id）
input_token_index = dict(
    [(char, i) for i, char in enumerate(input_characters)])
target_token_index = dict(
    [(char, i) for i, char in enumerate(target_characters)])
# 初始化
encoder_input_data = np.zeros(
    (len(input_texts), max_encoder_seq_length, num_encoder_tokens),
    dtype='float32')
decoder_input_data = np.zeros(
    (len(input_texts), max_decoder_seq_length, num_decoder_tokens),
    dtype='float32')
decoder_target_data = np.zeros(
    (len(input_texts), max_decoder_seq_length, num_decoder_tokens),
    dtype='float32')
print(encoder_input_data.shape)
# 訓練測試
for i, (input_text, target_text) in enumerate(zip(input_texts, target_texts)):
    for t, char in enumerate(input_text):
        encoder_input_data[i, t, input_token_index[char]] = 1.
    for t, char in enumerate(target_text):
        # decoder_target_data比decoder_input_data提前一個時間步長
        decoder_input_data[i, t, target_token_index[char]] = 1.
        if t > 0:
            # decoder_target_data will be ahead by one timestep
            # and will not include the start character.
            decoder_target_data[i, t - 1, target_token_index[char]] = 1.
# 定義輸入序列並處理它
encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
# 我們丟棄' encoder_output '，只保留狀態
encoder_states = [state_h, state_c]

# 設定解碼器，使用' encoder_states '作為初始狀態
decoder_inputs = Input(shape=(None, num_decoder_tokens))
# 我們設定解碼器以返回完整的輸出序列，並返回內部狀態。我們不在訓練模型中使用返回狀態，但是我們將在推理中使用它們。
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
                                     initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)

# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
#model.load_weights('s2s.h5')
# Run training
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
model.fit([encoder_input_data, decoder_input_data], decoder_target_data,
          batch_size=batch_size,
          epochs=epochs,
          validation_split=0.2)
# 儲存模型
model.save('s2s.h5')

# 接下來:推理模式(抽樣)
#  Here's the drill:
# 1)編碼輸入，檢索初始解碼器狀態
# 2)以初始狀態和“序列開始”token作為目標執行一個解碼器步驟。輸出將是下一個目標token
# 3)重複當前目標token和當前狀態


# 定義抽樣模型
encoder_model = Model(encoder_inputs, encoder_states)
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(
    decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model(
    [decoder_inputs] + decoder_states_inputs,
    [decoder_outputs] + decoder_states)
# 反向查詢令牌索引，將序列解碼回可讀的內容。
reverse_input_char_index = dict(
    (i, char) for char, i in input_token_index.items())
reverse_target_char_index = dict(
    (i, char) for char, i in target_token_index.items())

def decode_sequence(input_seq):
    # 將輸入編碼為狀態向量
    states_value = encoder_model.predict(input_seq)
    # 生成長度為1的空目標序列
    target_seq = np.zeros((1, 1, num_decoder_tokens))
    # 用起始字元填充目標序列的第一個字元。
    target_seq[0, 0, target_token_index['\t']] = 1.
    # 對一批序列的抽樣迴圈(為了簡化，這裡我們假設批大小為1)
    stop_condition = False
    decoded_sentence = ''
    while not stop_condition:
        output_tokens, h, c = decoder_model.predict(
            [target_seq] + states_value)
        # Sample a token
        sampled_token_index = np.argmax(output_tokens[0, -1, :])
        sampled_char = reverse_target_char_index[sampled_token_index]
        decoded_sentence += sampled_char
        # 退出條件:到達最大長度或找到停止字元。
        if (sampled_char == '\n' or len(decoded_sentence) > max_decoder_seq_length):
            stop_condition = True
        # 更新目標序列(長度1)
        target_seq = np.zeros((1, 1, num_decoder_tokens))
        target_seq[0, 0, sampled_token_index] = 1.
        # 更新狀態
        states_value = [h, c]
    return decoded_sentence
for seq_index in range(100):
    # 取一個序列(訓練測試的一部分)來嘗試解碼
    input_seq = encoder_input_data[seq_index: seq_index + 1]
    decoded_sentence = decode_sequence(input_seq)
    print('-')
    print('Input sentence:', input_texts[seq_index])
    print('Decoded sentence:', decoded_sentence)

資料集下載：http://www.manythings.org/anki/fra-eng.zip