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(' ') for index,line in enumerate(lines[: min(num_samples, len(lines) - 1)]): input_text, target_text = line.split(' ') target_text = ' ' + target_text + ' ' 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)) # 统计source和target的字符数 num_encoder_tokens = len(input_characters) num_decoder_tokens = len(target_characters) # 取出最长的句子的长度 max_encoder_seq_length = max([len(txt) for txt in input_texts]) max_decoder_seq_length = max([len(txt) for txt in target_texts]) # 打印具体的信息 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) # 将它们转化为id的形式存储（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) # 训练测试 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提前一个时间步长 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. # 定义输入序列并处理它 encoder_inputs = Input(shape=(None, num_encoder_tokens)) encoder = LSTM(latent_dim, return_state=True) encoder_outputs, state_h, state_c = encoder(encoder_inputs) # 我们丢弃' encoder_output '，只保留状态 encoder_states = [state_h, state_c] # 设置解码器，使用' encoder_states '作为初始状态 decoder_inputs = Input(shape=(None, num_decoder_tokens)) # 我们设置解码器以返回完整的输出序列，并返回内部状态。我们不在训练模型中使用返回状态，但是我们将在推理中使用它们。 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) # 保存模型 model.save('s2s.h5') # 接下来:推理模式(抽样) # Here's the drill: # 1)编码输入，检索初始解码器状态 # 2)以初始状态和“序列开始”token作为目标运行一个解码器步骤。输出将是下一个目标token # 3)重复当前目标token和当前状态 # 定义抽样模型 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) # 反向查找令牌索引，将序列解码回可读的内容。 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): # 将输入编码为状态向量 states_value = encoder_model.predict(input_seq) # 生成长度为1的空目标序列 target_seq = np.zeros((1, 1, num_decoder_tokens)) # 用起始字符填充目标序列的第一个字符。 target_seq[0, 0, target_token_index[' ']] = 1. # 对一批序列的抽样循环(为了简化，这里我们假设批大小为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 # 退出条件:到达最大长度或找到停止字符。 if (sampled_char == ' ' or len(decoded_sentence) > max_decoder_seq_length): stop_condition = True # 更新目标序列(长度1) target_seq = np.zeros((1, 1, num_decoder_tokens)) target_seq[0, 0, sampled_token_index] = 1. # 更新状态 states_value = [h, c] return decoded_sentence for seq_index in range(100): # 取一个序列(训练测试的一部分)来尝试解码 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)
数据集下载：http://www.manythings.org/anki/fra-eng.zip