import torch
from torch import nn
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_hiddens = 256
num_epochs, num_steps, batch_size, clipping_theta = 160, 35, 32, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']
lr = 1e-2 # 注意调整学习率
# print("using GRU")
# gru_layer = nn.GRU(input_size=vocab_size, hidden_size=num_hiddens)
# model = d2l.RNNModel(gru_layer, vocab_size)
print("using LSTM")
lstm_layer = nn.LSTM(input_size=vocab_size, hidden_size=num_hiddens)
model = d2l.RNNModel(lstm_layer, vocab_size)
d2l.train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
corpus_indices, idx_to_char, char_to_idx,
num_epochs, num_steps, lr, clipping_theta,
batch_size, pred_period, pred_len, prefixes)
import time
import math
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()
# one-hot
def one_hot(x, n_class, dtype=torch.float32):
x = x.long() # 转成Int64
res = torch.zeros(x.shape[0], n_class, dtype=dtype, device=x.device) # 为x中每一个样本生成一个n_class维全0向量
res.scatter_(1, x.view(-1, 1), 1) # dim=1 行维度，view(-1,1) 是index即那个位置被替换成1，最后一个1是source，如果是2 就相当于一个位置是2其余是0
return res
def to_onehot(x, n_class):
# x shape (batch seq_len) output shape seq_len elements of (batch, n_class)
# 例如输入x 10个样本 窗口大小是5 x shaop = (10, 5)， 词库大小是2000
# output 是5个 （10，2000）的10个onehot向量组成的矩阵
return [one_hot(x[:, i], n_class) for i in range(x.shape[1])] # 即为窗口内每一个字符生成onehot向量
# 初始化参数
num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
def get_params():
