【23-24 秋学期】NNDL 作业9 RNN

【23-24 秋学期】NNDL 作业9 RNN - SRN

简单循环网络（Simple Recurrent Network，SRN）只有一个隐藏层的神经网络．

1. 实现SRN

（1）使用Numpy

（2）在1的基础上，增加激活函数tanh

（3）使用nn.RNNCell实现

（4）使用nn.RNN实现

2. 实现“序列到序列”

3. “编码器-解码器”的简单实现

4.简单总结nn.RNNCell、nn.RNN

5.谈一谈对“序列”、“序列到序列”的理解

6.总结本周理论课和作业，写心得体会

1. 实现SRN

（1）使用Numpy

import numpy as npinputs = 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_h2output_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 npinputs = 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_h2output_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 torchbatch_size = 1
seq_len = 3  # 序列长度
input_size = 2  # 输入序列维度
hidden_size = 2  # 隐藏层维度
output_size = 2  # 输出层维度# RNNCell
cell = torch.nn.RNNCell(input_size=input_size, hidden_size=hidden_size)
# 初始化参数 https://zhuanlan.zhihu.com/p/342012463
for name, param in cell.named_parameters():if name.startswith("weight"):torch.nn.init.ones_(param)else:torch.nn.init.zeros_(param)
# 线性层
liner = torch.nn.Linear(hidden_size, output_size)
liner.weight.data = torch.Tensor([[1, 1], [1, 1]])
liner.bias.data = torch.Tensor([0.0])seq = torch.Tensor([[[1, 1]],[[1, 1]],[[2, 2]]])
hidden = torch.zeros(batch_size, hidden_size)
output = torch.zeros(batch_size, output_size)for idx, input in enumerate(seq):print('=' * 20, idx, '=' * 20)print('Input :', input)print('hidden :', hidden)hidden = cell(input, hidden)output = liner(hidden)print('output :', output)

（4）使用nn.RNN实现

import torchbatch_size = 1
seq_len = 3
input_size = 2
hidden_size = 2
num_layers = 1
output_size = 2cell = 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"):torch.nn.init.ones_(param)else:torch.nn.init.zeros_(param)# 线性层
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('Input :', inputs[0])
print('hidden:', 0, 0)
print('Output:', liner(out[0]))
print('--------------------------------------')
print('Input :', inputs[1])
print('hidden:', out[0])
print('Output:', liner(out[1]))
print('--------------------------------------')
print('Input :', inputs[2])
print('hidden:', out[1])
print('Output:', liner(out[2]))