《动手学深度学习》(PyTorch版)代码注释 - 36 【LSTM_with_zero】

说明

本博客代码来自开源项目：《动手学深度学习》(PyTorch版)
并且在博主学习的理解上对代码进行了大量注释，方便理解各个函数的原理和用途

配置环境

使用环境：python3.8
平台：Windows10
IDE：PyCharm

此节说明

此节对应书本上6.8节
此节功能为：长短期记忆（LSTM）的从零实现
由于次节相对容易理解，代码注释量较少

代码

# 本书链接https://tangshusen.me/Dive-into-DL-PyTorch/#/
# 6.8 长短期记忆（LSTM）
# 注释：黄文俊
# E-mail：hurri_cane@qq.com


import numpy as np
import torch
from torch import nn, optim
import torch.nn.functional as F

import sys
sys.path.append("..")
import d2lzh_pytorch as d2l
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

(corpus_indices, char_to_idx, idx_to_char, vocab_size) = d2l.load_data_jay_lyrics()

num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
print('will use', device)

def get_params():
    def _one(shape):
        ts = torch.tensor(np.random.normal(0, 0.01, size=shape), device=device, dtype=torch.float32)
        return torch.nn.Parameter(ts, requires_grad=True)
    def _three():
        return (_one((num_inputs, num_hiddens)),
                _one((num_hiddens, num_hiddens)),
                torch.nn.Parameter(torch.zeros(num_hiddens, device=device, dtype=torch.float32), requires_grad=True))

    W_xi, W_hi, b_i = _three()  # 输入门参数
    W_xf, W_hf, b_f = _three()  # 遗忘门参数
    W_xo, W_ho, b_o = _three()  # 输出门参数
    W_xc, W_hc, b_c = _three()  # 候选记忆细胞参数

    # 输出层参数
    W_hq = _one((num_hiddens, num_outputs))
    b_q = torch.nn.Parameter(torch.zeros(num_outputs, device=device, dtype=torch.float32), requires_grad=True)
    return nn.ParameterList([W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc, b_c, W_hq, b_q])

# 定义模型
def init_lstm_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device),
            torch.zeros((batch_size, num_hiddens), device=device))


# lstm模型
# lstm模型的最终输出还是torch.matmul(H, W_hq) + b_q
# 只是在输出这个的基础上针对RNN输出返回隐藏层状态H外还多返回了细胞记忆C
# 而细胞记忆C是通过隐藏门、输入门计算得到的；隐藏层状态H是通过隐藏门、输入门、遗忘门共同得到
def lstm(inputs, state, params):
    [W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc, b_c, W_hq, b_q] = params
    (H, C) = state
    outputs = []
    for X in inputs:
        I = torch.sigmoid(torch.matmul(X, W_xi) + torch.matmul(H, W_hi) + b_i)
        F = torch.sigmoid(torch.matmul(X, W_xf) + torch.matmul(H, W_hf) + b_f)
        O = torch.sigmoid(torch.matmul(X, W_xo) + torch.matmul(H, W_ho) + b_o)
        C_tilda = torch.tanh(torch.matmul(X, W_xc) + torch.matmul(H, W_hc) + b_c)
        C = F * C + I * C_tilda
        H = O * C.tanh()
        Y = torch.matmul(H, W_hq) + b_q
        outputs.append(Y)
    return outputs, (H, C)



num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']

d2l.train_and_predict_rnn(lstm, get_params, init_lstm_state, num_hiddens,
                          vocab_size, device, corpus_indices, idx_to_char,
                          char_to_idx, False, num_epochs, num_steps, lr,
                          clipping_theta, batch_size, pred_period, pred_len,
                          prefixes)


print("*"*50)