深度学习作业9-RNN-SRN-Seq2Seq

1. 实现SRN（Simple Recurrent Network）

（1）使用Numpy

import numpy as np

inputs = np.array([[1., 1.],
                   [1., 1.],
                   [2., 2.]])  # 初始化输入序列
print('inputs is ', inputs)

state_t = np.zeros(2, )  # 初始化存储器
print('state_t is ', state_t)

w1, w2, w3, w4, w5, w6, w7, w8 = 1., 1., 1., 1., 1., 1., 1., 1.
U1, U2, U3, U4 = 1., 1., 1., 1.
print('--------------------------------------')
for input_t in inputs:
    print('inputs is ', input_t)
    print('state_t is ', state_t)
    in_h1 = np.dot([w1, w3], input_t) + np.dot([U2, U4], state_t)
    in_h2 = np.dot([w2, w4], input_t) + np.dot([U1, U3], state_t)
    state_t = in_h1, in_h2
    output_y1 = np.dot([w5, w7], [in_h1, in_h2])
    output_y2 = np.dot([w6, w8], [in_h1, in_h2])
    print('output_y is ', output_y1, output_y2)
    print('---------------')

（2）在1的基础上，增加激活函数tanh

import numpy as np

inputs = np.array([[1., 1.],
                   [1., 1.],
                   [2., 2.]])  # 初始化输入序列
print('inputs is ', inputs)

state_t = np.zeros(2, )  # 初始化存储器
print('state_t is ', state_t)

w1, w2, w3, w4, w5, w6, w7, w8 = 1., 1., 1., 1., 1., 1., 1., 1.
U1, U2, U3, U4 = 1., 1., 1., 1.
print('--------------------------------------')
for input_t in inputs:
    print('inputs is ', input_t)
    print('state_t is ', state_t)
    in_h1 = np.tanh(np.dot([w1, w3], input_t) + np.dot([U2, U4], state_t))
    in_h2 = np.tanh(np.dot([w2, w4], input_t) + np.dot([U1, U3], state_t))
    state_t = in_h1, in_h2
    output_y1 = np.dot([w5, w7], [in_h1, in_h2])
    output_y2 = np.dot([w6, w8], [in_h1, in_h2])
    print('output_y is ', output_y1, output_y2)
    print('---------------')

（3）使用nn.RNNCell实现

import torch

batch_size = 1  # 样本个数
seq_len = 3  # 序列的长度
input_size = 2  # 输入特征的维度
hidden_size = 2  # 隐藏层神经元
num_layers = 1  # 网络的层数
output_size = 2  # 输出特征的维度

cell = torch.nn.RNN(input_size=input_size, hidden_size=hidden_size, num_layers=num_layers)

for name, param in cell.named_parameters():  # 初始化参数
    if name.startswith("weight"):  # 权重
        torch.nn.init.ones_(param)
    else:  # 偏置
        torch.nn.init.zeros_(param)

# 线性层构造
liner = torch.nn.Linear(hidden_size, output_size)
liner.weight.data = torch.Tensor([[1, 1], [1, 1]])
liner.bias.data = torch.Tensor([0.0])

inputs = torch.Tensor([[[1, 1]],
                       [[1, 1]],
                       [[2, 2]]])
hidden = torch.zeros(num_layers, batch_size, hidden_size)
out, hidden = cell(inputs, hidden)

print(f"------------第1个输入------------")
print('Input :', inputs[0])
print('hidden:', 0, 0)
print('Output:', liner(out[0]))

print(f"------------第2个输入------------")
print('Input :', inputs[1])
print(&