《动手学深度学习》(PyTorch版)代码注释 - 34 【GRU_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6.7节
此节功能为：门控循环单元（GRU）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/#/chapter03_DL-basics/3.8_mlp
# 6.7 门控循环单元（GRU）
# 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_xz, W_hz, b_z = _three()  # 更新门参数
    W_xr, W_hr, b_r = _three()  # 重置门参数
    W_xh, W_hh, b_h = _three()  # 候选隐藏状态参数

    # 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_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q])


def init_gru_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device), )



# 重置门有助于捕捉时间序列里短期的依赖关系。
# 更新门有助于捕捉时间序列里长期的依赖关系。

# 据门控循环单元的计算表达式定义模型
def gru(inputs, state, params):
    W_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q = params
    H, = state
    outputs = []
    for X in inputs:
        Z = torch.sigmoid(torch.matmul(X, W_xz) + torch.matmul(H, W_hz) + b_z)
        R = torch.sigmoid(torch.matmul(X, W_xr) + torch.matmul(H, W_hr) + b_r)
        H_tilda = torch.tanh(torch.matmul(X, W_xh) + torch.matmul(R * H, W_hh) + b_h)
        H = Z * H + (1 - Z) * H_tilda
        Y = torch.matmul(H, W_hq) + b_q
        outputs.append(Y)
    return outputs, (H,)




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(gru, get_params, init_gru_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)