【如何训练一个中英翻译模型】LSTM机器翻译模型部署（三）-Toy模板网

这篇具有很好参考价值的文章主要介绍了【如何训练一个中英翻译模型】LSTM机器翻译模型部署（三）。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

系列文章

【如何训练一个中英翻译模型】LSTM机器翻译seq2seq字符编码（一）
【如何训练一个中英翻译模型】LSTM机器翻译模型训练与保存（二）
【如何训练一个中英翻译模型】LSTM机器翻译模型部署（三）
【如何训练一个中英翻译模型】LSTM机器翻译模型部署之onnx（python）（四）

模型部署也是很重要的一部分，这里先讲基于python的部署，后面我们还要将模型部署到移动端。
细心的小伙伴会发现前面的文章在模型保存之后进行模型推理时，我们使用的数据是在训练之前我们对数据进行处理的encoder_input_data中读取，而不是我们手动输入的，那么这一章主要来解决自定义输入推理的问题

1、加载字符文件

首先，我们根据【如何训练一个中译英翻译器】LSTM机器翻译模型训练与保存（二）的操作，到最后
会得到这样的三个文件：input_words.txt，target_words.txt，config.json
需要逐一进行加载
进行加载

# 加载字符
# 从 input_words.txt 文件中读取字符串
with open('input_words.txt', 'r') as f:
    input_words = f.readlines()
    input_characters = [line.rstrip('\n') for line in input_words]

# 从 target_words.txt 文件中读取字符串
with open('target_words.txt', 'r', newline='') as f:
    target_words = [line.strip() for line in f.readlines()]
    target_characters = [char.replace('\\t', '\t').replace('\\n', '\n') for char in target_words]

#字符处理，以方便进行编码
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)])

# something readable.
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())
num_encoder_tokens = len(input_characters) # 英文字符数量
num_decoder_tokens = len(target_characters) # 中文文字数量

读取配置文件

import json
with open('config.json', 'r') as file:
    loaded_data = json.load(file)

# 从加载的数据中获取max_encoder_seq_length和max_decoder_seq_length的值
max_encoder_seq_length = loaded_data["max_encoder_seq_length"]
max_decoder_seq_length = loaded_data["max_decoder_seq_length"]

2、加载权重文件

# 加载权重
from keras.models import load_model
encoder_model = load_model('encoder_model.h5')
decoder_model = load_model('decoder_model.h5')

3、推理模型搭建

def decode_sequence(input_seq):
    # Encode the input as state vectors.
    states_value = encoder_model.predict(input_seq)

    # Generate empty target sequence of length 1.
    target_seq = np.zeros((1, 1, num_decoder_tokens))
    # Populate the first character of target sequence with the start character.
    target_seq[0, 0, target_token_index['\t']] = 1.
    # this target_seq you can treat as initial state

    # Sampling loop for a batch of sequences
    # (to simplify, here we assume a batch of size 1).
    stop_condition = False
    decoded_sentence = ''
    while not stop_condition:
        output_tokens, h, c = decoder_model.predict([target_seq] + states_value)

        # Sample a token
        # argmax: Returns the indices of the maximum values along an axis
        # just like find the most possible char
        sampled_token_index = np.argmax(output_tokens[0, -1, :])
        # find char using index
        sampled_char = reverse_target_char_index[sampled_token_index]
        # and append sentence
        decoded_sentence += sampled_char

        # Exit condition: either hit max length
        # or find stop character.
        if (sampled_char == '\n' or len(decoded_sentence) > max_decoder_seq_length):
            stop_condition = True

        # Update the target sequence (of length 1).
        # append then ?
        # creating another new target_seq
        # and this time assume sampled_token_index to 1.0
        target_seq = np.zeros((1, 1, num_decoder_tokens))
        target_seq[0, 0, sampled_token_index] = 1.

        # Update states
        # update states, frome the front parts
        states_value = [h, c]

    return decoded_sentence

4、进行推理

import numpy as np

input_text = "Call me."
encoder_input_data = np.zeros(
    (1,max_encoder_seq_length, num_encoder_tokens),
    dtype='float32')
for t, char in enumerate(input_text):
    print(char)
    # 3D vector only z-index has char its value equals 1.0
    encoder_input_data[0,t, input_token_index[char]] = 1.


input_seq = encoder_input_data
decoded_sentence = decode_sequence(input_seq)
print('-')
print('Input sentence:', input_text)
print('Decoded sentence:', decoded_sentence)