56门控循环单元GRU

import torch
from torch import nn
from d2l import torch as d2l

"""
额外的控制单元
"""

batch_size, num_steps = 32, 35
train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)

# 初始化模型参数
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

    def three():
        return (normal((num_inputs, num_hiddens)),
                normal((num_hiddens, num_hiddens)),
                torch.zeros(num_hiddens, device=device))

    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()  # 候选隐状态参数
    # 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_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q]
    for param in params:
        param.requires_grad_(True)
    return params

# 定义隐状态的初始化函数
def init_gru_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device), )

# 定义门控循环单元模型
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 = []
    # (num_steps, batch_size, vocab_size)
    for X in inputs:
        # 
标签：vocab,hiddens,GRU,torch,56,num,device,门控,size	

来源： https://www.cnblogs.com/g932150283/p/16442829.html