54 循环神经网络 RNN【动手学深度学习v2】

%matplotlib inline
import math
import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l
 
batch_size, num_steps = 32, 35
train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)
 
F.one_hot(torch.tensor([0, 2]), len(vocab))
 
 
X = torch.arange(10).reshape((2, 5))
F.one_hot(X.T, 28).shape
 
 
def get_params(vocab_size, num_hiddens, device):
    num_inputs = num_outputs = vocab_size
 
    def normal(shape):
        return torch.randn(size=shape, device=device) * 0.01
 
    # 隐藏层参数
    W_xh = normal((num_inputs, num_hiddens))
    W_hh = normal((num_hiddens, num_hiddens))
    b_h = torch.zeros(num_hiddens, device=device)
    # 输出层参数
    W_hq = normal((num_hiddens, num_outputs))
    b_q = torch.zeros(num_outputs, device=device)
    # 附加梯度
    params = [W_xh, W_hh, b_h, W_hq, b_q]
    for param in params:
        param.requires_grad_(True)
    return params

以后根据学习进度会随时补偿每个笔记的知识的