动手学深度学习PyTorch版-循环神经网络进阶

循环神经网络进阶

GRU

数据载入

import os
os.listdir('/home/kesci/input')

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

import sys
sys.path.append("../input/")
import d2l_jay9460 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()

初始化参数

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) #正态分布
        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):   #隐藏状态初始化
    return (torch.zeros((batch_size, num_hiddens), device