NNDL 作业8：RNN - 简单循环网络

最新推荐文章于 2023-12-06 23:51:40 发布

zc.9495

最新推荐文章于 2023-12-06 23:51:40 发布

阅读量435

点赞数 1

文章标签： rnn python 深度学习

本文链接：https://blog.csdn.net/vvhvj/article/details/127834579

版权

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

1. 使用Numpy实现SRN

在这里插入图片描述

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('---------------')

实验结果：

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

在这里插入图片描述

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('---------------')

实验结果：

inputs is  [[1. 1.]
 [1. 1.]
 [2. 2.]]
state_t is  [0. 0.]
--------------------------------------
inputs is  [1. 1.]
state_t is  [0. 0.]
output_y is  1.9280551601516338 1.9280551601516338
---------------
inputs is  [1. 1.]
state_t is  (0.9640275800758169, 0.9640275800758169)
output_y is  1.9984510891336251 1.9984510891336251
---------------
inputs is  [2. 2.]
state_t is  (0.9992255445668126, 0.9992255445668126)
output_y is  1.9999753470497836 1.9999753470497836
---------------

3. 分别使用nn.RNNCell、nn.RNN实现SRN

在这里插入图片描述
nn.RNNCell：

import torch
 
batch_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)

实验结果：

==================== 0 ====================
Input : tensor([[1., 1.]])
hidden : tensor([[0., 0.]])
output : tensor([[1.9281, 1.9281]], grad_fn=<AddmmBackward>)
==================== 1 ====================
Input : tensor([[1., 1.]])
hidden : tensor([[0.9640, 0.9640]], grad_fn=<TanhBackward>)
output : tensor([[1.9985, 1.9985]], grad_fn=<AddmmBackward>)
==================== 2 ====================
Input : tensor([[2., 2.]])
hidden : tensor([[0.9992, 0.9992]], grad_fn=<TanhBackward>)
output : tensor([[2.0000, 2.0000]], grad_fn=<AddmmBackward>)

nn.RNN：

import torch
 
batch_size = 1
seq_len = 3
input_size = 2
hidden_size = 2
num_layers = 1
output_size = 2
 
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"):
        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]))

实验结果：

Input : tensor([[1., 1.]])
hidden: 0 0
Output: tensor([[1.9281, 1.9281]], grad_fn=<AddmmBackward>)
--------------------------------------
Input : tensor([[1., 1.]])
hidden: tensor([[0.9640, 0.9640]], grad_fn=<SelectBackward>)
Output: tensor([[1.9985, 1.9985]], grad_fn=<AddmmBackward>)
--------------------------------------
Input : tensor([[2., 2.]])
hidden: tensor([[0.9992, 0.9992]], grad_fn=<SelectBackward>)
Output: tensor([[2.0000, 2.0000]], grad_fn=<AddmmBackward>)

4. 分析“二进制加法” 源代码（选做）

在这里插入图片描述

import copy, numpy as np
 
np.random.seed(0)
 
 
#定义sigmoid函数
def sigmoid(x):
    output = 1 / (1 + np.exp(-x))
    return output
 
 
#定义sigmoid导数
def sigmoid_output_to_derivative(output):
    return output * (1 - output)
 
 
#训练数据的产生
int2binary = {}
binary_dim = 8 #定义二进制位的长度
 
largest_number = pow(2, binary_dim)#定义数据的最大值
binary = np.unpackbits(
    np.array([range(largest_number)], dtype=np.uint8).T, axis=1)#函数产生包装所有符合的二进制序列
for i in range(largest_number):#遍历从0-256的值
    int2binary[i] = binary[i]#对于每个整型值赋值二进制序列
print(int2binary)
# 产生输入变量
alpha = 0.1         #设置更新速度（学习率）
input_dim = 2       #输入维度大小
hidden_dim = 16     #隐藏层维度大小
output_dim = 1      #输出维度大小
 
# 随机产生网络权重
synapse_0 = 2 * np.random.random((input_dim, hidden_dim)) - 1
synapse_1 = 2 * np.random.random((hidden_dim, output_dim)) - 1
synapse_h = 2 * np.random.random((hidden_dim, hidden_dim)) - 1
 
#梯度初始值设置为0
synapse_0_update = np.zeros_like(synapse_0)
synapse_1_update = np.zeros_like(synapse_1)
synapse_h_update = np.zeros_like(synapse_h)
 
#训练逻辑
for j in range(10000):
 
    # 产生一个简单的加法问题
    a_int = np.random.randint(largest_number / 2)  # 产生一个加法操作数
    a = int2binary[a_int]   # 找到二进制序列编码
 
    b_int = np.random.randint(largest_number / 2)  # 产生另一个加法操作数
    b = int2binary[b_int]   # 找到二进制序列编码
 
    # 计算正确值（标签值）
    c_int = a_int + b_int
    c = int2binary[c_int]   # 得到正确的结果序列
 
    # 设置存储器，存储中间值（记忆功能）
    d = np.zeros_like(c)
 
    overallError = 0        #设置误差
 
    layer_2_deltas = list()
    layer_1_values = list()
    layer_1_values.append(np.zeros(hidden_dim))
 
    # moving along the positions in the binary encoding
    for position in range(binary_dim):
        # 产生输入和输出
        X = np.array([[a[binary_dim - position - 1], b[binary_dim - position - 1]]])
        y = np.array([[c[binary_dim - position - 1]]]).T
 
        # 隐藏层计算
        layer_1 = sigmoid(np.dot(X, synapse_0) + np.dot(layer_1_values[-1], synapse_h))
 
        # 输出层
        layer_2 = sigmoid(np.dot(layer_1, synapse_1))
        # 计算差别
        layer_2_error = y - layer_2
        #计算每个梯度
        layer_2_deltas.append((layer_2_error) * sigmoid_output_to_derivative(layer_2))
        #计算所有损失
        overallError += np.abs(layer_2_error[0])
 
        # 编码记忆的中间值
        d[binary_dim - position - 1] = np.round(layer_2[0][0])
 
        # 拷贝副本
        layer_1_values.append(copy.deepcopy(layer_1))
 
    future_layer_1_delta = np.zeros(hidden_dim)
 
    for position in range(binary_dim):
        X = np.array([[a[position], b[position]]])
        layer_1 = layer_1_values[-position - 1]
        prev_layer_1 = layer_1_values[-position - 2]
 
        # 输出层误差
        layer_2_delta = layer_2_deltas[-position - 1]
        # 隐藏层误差
        layer_1_delta = (future_layer_1_delta.dot(synapse_h.T) + layer_2_delta.dot(
            synapse_1.T)) * sigmoid_output_to_derivative(layer_1)
 
        # 计算梯度
        synapse_1_update += np.atleast_2d(layer_1).T.dot(layer_2_delta)
        synapse_h_update += np.atleast_2d(prev_layer_1).T.dot(layer_1_delta)
        synapse_0_update += X.T.dot(layer_1_delta)
 
        future_layer_1_delta = layer_1_delta
    #梯度下降
    synapse_0 += synapse_0_update * alpha
    synapse_1 += synapse_1_update * alpha
    synapse_h += synapse_h_update * alpha
    #重新初始化
    synapse_0_update *= 0
    synapse_1_update *= 0
    synapse_h_update *= 0
 
    # 打印训练过程
    if (j % 1000 == 0):
        print("Error:" + str(overallError))
        print("Pred:" + str(d))
        print("True:" + str(c))
        out = 0
        for index, x in enumerate(reversed(d)):
            out += x * pow(2, index)
        print(str(a_int) + " + " + str(b_int) + " = " + str(out))
        print("------------")

实验结果：

{0: array([0, 0, 0, 0, 0, 0, 0, 0], dtype=uint8), 1: array([0, 0, 0, 0, 0, 0, 0, 1], dtype=uint8), 2: array([0, 0, 0, 0, 0, 0, 1, 0], dtype=uint8), 3: array([0, 0, 0, 0, 0, 0, 1, 1], dtype=uint8), 4: array([0, 0, 0, 0, 0, 1, 0, 0], dtype=uint8), 5: array([0, 0, 0, 0, 0, 1, 0, 1], dtype=uint8), 6: array([0, 0, 0, 0, 0, 1, 1, 0], dtype=uint8), 7: array([0, 0, 0, 0, 0, 1, 1, 1], dtype=uint8), 8: array([0, 0, 0, 0, 1, 0, 0, 0], dtype=uint8), 9: array([0, 0, 0, 0, 1, 0, 0, 1], dtype=uint8), 10: array([0, 0, 0, 0, 1, 0, 1, 0], dtype=uint8), 11: array([0, 0, 0, 0, 1, 0, 1, 1], dtype=uint8), 12: array([0, 0, 0, 0, 1, 1, 0, 0], dtype=uint8), 13: array([0, 0, 0, 0, 1, 1, 0, 1], dtype=uint8), 14: array([0, 0, 0, 0, 1, 1, 1, 0], dtype=uint8), 15: array([0, 0, 0, 0, 1, 1, 1, 1], dtype=uint8), 16: array([0, 0, 0, 1, 0, 0, 0, 0], dtype=uint8), 17: array([0, 0, 0, 1, 0, 0, 0, 1], dtype=uint8), 18: array([0, 0, 0, 1, 0, 0, 1, 0], dtype=uint8), 19: array([0, 0, 0, 1, 0, 0, 1, 1], dtype=uint8), 20: array([0, 0, 0, 1, 0, 1, 0, 0], dtype=uint8), 21: array([0, 0, 0, 1, 0, 1, 0, 1], dtype=uint8), 22: array([0, 0, 0, 1, 0, 1, 1, 0], dtype=uint8), 23: array([0, 0, 0, 1, 0, 1, 1, 1], dtype=uint8), 24: array([0, 0, 0, 1, 1, 0, 0, 0], dtype=uint8), 25: array([0, 0, 0, 1, 1, 0, 0, 1], dtype=uint8), 26: array([0, 0, 0, 1, 1, 0, 1, 0], dtype=uint8), 27: array([0, 0, 0, 1, 1, 0, 1, 1], dtype=uint8), 28: array([0, 0, 0, 1, 1, 1, 0, 0], dtype=uint8), 29: array([0, 0, 0, 1, 1, 1, 0, 1], dtype=uint8), 30: array([0, 0, 0, 1, 1, 1, 1, 0], dtype=uint8), 31: array([0, 0, 0, 1, 1, 1, 1, 1], dtype=uint8), 32: array([0, 0, 1, 0, 0, 0, 0, 0], dtype=uint8), 33: array([0, 0, 1, 0, 0, 0, 0, 1], dtype=uint8), 34: array([0, 0, 1, 0, 0, 0, 1, 0], dtype=uint8), 35: array([0, 0, 1, 0, 0, 0, 1, 1], dtype=uint8), 36: array([0, 0, 1, 0, 0, 1, 0, 0], dtype=uint8), 37: array([0, 0, 1, 0, 0, 1, 0, 1], dtype=uint8), 38: array([0, 0, 1, 0, 0, 1, 1, 0], dtype=uint8), 39: array([0, 0, 1, 0, 0, 1, 1, 1], dtype=uint8), 40: array([0, 0, 1, 0, 1, 0, 0, 0], dtype=uint8), 41: array([0, 0, 1, 0, 1, 0, 0, 1], dtype=uint8), 42: array([0, 0, 1, 0, 1, 0, 1, 0], dtype=uint8), 43: array([0, 0, 1, 0, 1, 0, 1, 1], dtype=uint8), 44: array([0, 0, 1, 0, 1, 1, 0, 0], dtype=uint8), 45: array([0, 0, 1, 0, 1, 1, 0, 1], dtype=uint8), 46: array([0, 0, 1, 0, 1, 1, 1, 0], dtype=uint8), 47: array([0, 0, 1, 0, 1, 1, 1, 1], dtype=uint8), 48: array([0, 0, 1, 1, 0, 0, 0, 0], dtype=uint8), 49: array([0, 0, 1, 1, 0, 0, 0, 1], dtype=uint8), 50: array([0, 0, 1, 1, 0, 0, 1, 0], dtype=uint8), 51: array([0, 0, 1, 1, 0, 0, 1, 1], dtype=uint8), 52: array([0, 0, 1, 1, 0, 1, 0, 0], dtype=uint8), 53: array([0, 0, 1, 1, 0, 1, 0, 1], dtype=uint8), 54: array([0, 0, 1, 1, 0, 1, 1, 0], dtype=uint8), 55: array([0, 0, 1, 1, 0, 1, 1, 1], dtype=uint8), 56: array([0, 0, 1, 1, 1, 0, 0, 0], dtype=uint8), 57: array([0, 0, 1, 1, 1, 0, 0, 1], dtype=uint8), 58: array([0, 0, 1, 1, 1, 0, 1, 0], dtype=uint8), 59: array([0, 0, 1, 1, 1, 0, 1, 1], dtype=uint8), 60: array([0, 0, 1, 1, 1, 1, 0, 0], dtype=uint8), 61: array([0, 0, 1, 1, 1, 1, 0, 1], dtype=uint8), 62: array([0, 0, 1, 1, 1, 1, 1, 0], dtype=uint8), 63: array([0, 0, 1, 1, 1, 1, 1, 1], dtype=uint8), 64: array([0, 1, 0, 0, 0, 0, 0, 0], dtype=uint8), 65: array([0, 1, 0, 0, 0, 0, 0, 1], dtype=uint8), 66: array([0, 1, 0, 0, 0, 0, 1, 0], dtype=uint8), 67: array([0, 1, 0, 0, 0, 0, 1, 1], dtype=uint8), 68: array([0, 1, 0, 0, 0, 1, 0, 0], dtype=uint8), 69: array([0, 1, 0, 0, 0, 1, 0, 1], dtype=uint8), 70: array([0, 1, 0, 0, 0, 1, 1, 0], dtype=uint8), 71: array([0, 1, 0, 0, 0, 1, 1, 1], dtype=uint8), 72: array([0, 1, 0, 0, 1, 0, 0, 0], dtype=uint8), 73: array([0, 1, 0, 0, 1, 0, 0, 1], dtype=uint8), 74: array([0, 1, 0, 0, 1, 0, 1, 0], dtype=uint8), 75: array([0, 1, 0, 0, 1, 0, 1, 1], dtype=uint8), 76: array([0, 1, 0, 0, 1, 1, 0, 0], dtype=uint8), 77: array([0, 1, 0, 0, 1, 1, 0, 1], dtype=uint8), 78: array([0, 1, 0, 0, 1, 1, 1, 0], dtype=uint8), 79: array([0, 1, 0, 0, 1, 1, 1, 1], dtype=uint8), 80: array([0, 1, 0, 1, 0, 0, 0, 0], dtype=uint8), 81: array([0, 1, 0, 1, 0, 0, 0, 1], dtype=uint8), 82: array([0, 1, 0, 1, 0, 0, 1, 0], dtype=uint8), 83: array([0, 1, 0, 1, 0, 0, 1, 1], dtype=uint8), 84: array([0, 1, 0, 1, 0, 1, 0, 0], dtype=uint8), 85: array([0, 1, 0, 1, 0, 1, 0, 1], dtype=uint8), 86: array([0, 1, 0, 1, 0, 1, 1, 0], dtype=uint8), 87: array([0, 1, 0, 1, 0, 1, 1, 1], dtype=uint8), 88: array([0, 1, 0, 1, 1, 0, 0, 0], dtype=uint8), 89: array([0, 1, 0, 1, 1, 0, 0, 1], dtype=uint8), 90: array([0, 1, 0, 1, 1, 0, 1, 0], dtype=uint8), 91: array([0, 1, 0, 1, 1, 0, 1, 1], dtype=uint8), 92: array([0, 1, 0, 1, 1, 1, 0, 0], dtype=uint8), 93: array([0, 1, 0, 1, 1, 1, 0, 1], dtype=uint8), 94: array([0, 1, 0, 1, 1, 1, 1, 0], dtype=uint8), 95: array([0, 1, 0, 1, 1, 1, 1, 1], dtype=uint8), 96: array([0, 1, 1, 0, 0, 0, 0, 0], dtype=uint8), 97: array([0, 1, 1, 0, 0, 0, 0, 1], dtype=uint8), 98: array([0, 1, 1, 0, 0, 0, 1, 0], dtype=uint8), 99: array([0, 1, 1, 0, 0, 0, 1, 1], dtype=uint8), 100: array([0, 1, 1, 0, 0, 1, 0, 0], dtype=uint8), 101: array([0, 1, 1, 0, 0, 1, 0, 1], dtype=uint8), 102: array([0, 1, 1, 0, 0, 1, 1, 0], dtype=uint8), 103: array([0, 1, 1, 0, 0, 1, 1, 1], dtype=uint8), 104: array([0, 1, 1, 0, 1, 0, 0, 0], dtype=uint8), 105: array([0, 1, 1, 0, 1, 0, 0, 1], dtype=uint8), 106: array([0, 1, 1, 0, 1, 0, 1, 0], dtype=uint8), 107: array([0, 1, 1, 0, 1, 0, 1, 1], dtype=uint8), 108: array([0, 1, 1, 0, 1, 1, 0, 0], dtype=uint8), 109: array([0, 1, 1, 0, 1, 1, 0, 1], dtype=uint8), 110: array([0, 1, 1, 0, 1, 1, 1, 0], dtype=uint8), 111: array([0, 1, 1, 0, 1, 1, 1, 1], dtype=uint8), 112: array([0, 1, 1, 1, 0, 0, 0, 0], dtype=uint8), 113: array([0, 1, 1, 1, 0, 0, 0, 1], dtype=uint8), 114: array([0, 1, 1, 1, 0, 0, 1, 0], dtype=uint8), 115: array([0, 1, 1, 1, 0, 0, 1, 1], dtype=uint8), 116: array([0, 1, 1, 1, 0, 1, 0, 0], dtype=uint8), 117: array([0, 1, 1, 1, 0, 1, 0, 1], dtype=uint8), 118: array([0, 1, 1, 1, 0, 1, 1, 0], dtype=uint8), 119: array([0, 1, 1, 1, 0, 1, 1, 1], dtype=uint8), 120: array([0, 1, 1, 1, 1, 0, 0, 0], dtype=uint8), 121: array([0, 1, 1, 1, 1, 0, 0, 1], dtype=uint8), 122: array([0, 1, 1, 1, 1, 0, 1, 0], dtype=uint8), 123: array([0, 1, 1, 1, 1, 0, 1, 1], dtype=uint8), 124: array([0, 1, 1, 1, 1, 1, 0, 0], dtype=uint8), 125: array([0, 1, 1, 1, 1, 1, 0, 1], dtype=uint8), 126: array([0, 1, 1, 1, 1, 1, 1, 0], dtype=uint8), 127: array([0, 1, 1, 1, 1, 1, 1, 1], dtype=uint8), 128: array([1, 0, 0, 0, 0, 0, 0, 0], dtype=uint8), 129: array([1, 0, 0, 0, 0, 0, 0, 1], dtype=uint8), 130: array([1, 0, 0, 0, 0, 0, 1, 0], dtype=uint8), 131: array([1, 0, 0, 0, 0, 0, 1, 1], dtype=uint8), 132: array([1, 0, 0, 0, 0, 1, 0, 0], dtype=uint8), 133: array([1, 0, 0, 0, 0, 1, 0, 1], dtype=uint8), 134: array([1, 0, 0, 0, 0, 1, 1, 0], dtype=uint8), 135: array([1, 0, 0, 0, 0, 1, 1, 1], dtype=uint8), 136: array([1, 0, 0, 0, 1, 0, 0, 0], dtype=uint8), 137: array([1, 0, 0, 0, 1, 0, 0, 1], dtype=uint8), 138: array([1, 0, 0, 0, 1, 0, 1, 0], dtype=uint8), 139: array([1, 0, 0, 0, 1, 0, 1, 1], dtype=uint8), 140: array([1, 0, 0, 0, 1, 1, 0, 0], dtype=uint8), 141: array([1, 0, 0, 0, 1, 1, 0, 1], dtype=uint8), 142: array([1, 0, 0, 0, 1, 1, 1, 0], dtype=uint8), 143: array([1, 0, 0, 0, 1, 1, 1, 1], dtype=uint8), 144: array([1, 0, 0, 1, 0, 0, 0, 0], dtype=uint8), 145: array([1, 0, 0, 1, 0, 0, 0, 1], dtype=uint8), 146: array([1, 0, 0, 1, 0, 0, 1, 0], dtype=uint8), 147: array([1, 0, 0, 1, 0, 0, 1, 1], dtype=uint8), 148: array([1, 0, 0, 1, 0, 1, 0, 0], dtype=uint8), 149: array([1, 0, 0, 1, 0, 1, 0, 1], dtype=uint8), 150: array([1, 0, 0, 1, 0, 1, 1, 0], dtype=uint8), 151: array([1, 0, 0, 1, 0, 1, 1, 1], dtype=uint8), 152: array([1, 0, 0, 1, 1, 0, 0, 0], dtype=uint8), 153: array([1, 0, 0, 1, 1, 0, 0, 1], dtype=uint8), 154: array([1, 0, 0, 1, 1, 0, 1, 0], dtype=uint8), 155: array([1, 0, 0, 1, 1, 0, 1, 1], dtype=uint8), 156: array([1, 0, 0, 1, 1, 1, 0, 0], dtype=uint8), 157: array([1, 0, 0, 1, 1, 1, 0, 1], dtype=uint8), 158: array([1, 0, 0, 1, 1, 1, 1, 0], dtype=uint8), 159: array([1, 0, 0, 1, 1, 1, 1, 1], dtype=uint8), 160: array([1, 0, 1, 0, 0, 0, 0, 0], dtype=uint8), 161: array([1, 0, 1, 0, 0, 0, 0, 1], dtype=uint8), 162: array([1, 0, 1, 0, 0, 0, 1, 0], dtype=uint8), 163: array([1, 0, 1, 0, 0, 0, 1, 1], dtype=uint8), 164: array([1, 0, 1, 0, 0, 1, 0, 0], dtype=uint8), 165: array([1, 0, 1, 0, 0, 1, 0, 1], dtype=uint8), 166: array([1, 0, 1, 0, 0, 1, 1, 0], dtype=uint8), 167: array([1, 0, 1, 0, 0, 1, 1, 1], dtype=uint8), 168: array([1, 0, 1, 0, 1, 0, 0, 0], dtype=uint8), 169: array([1, 0, 1, 0, 1, 0, 0, 1], dtype=uint8), 170: array([1, 0, 1, 0, 1, 0, 1, 0], dtype=uint8), 171: array([1, 0, 1, 0, 1, 0, 1, 1], dtype=uint8), 172: array([1, 0, 1, 0, 1, 1, 0, 0], dtype=uint8), 173: array([1, 0, 1, 0, 1, 1, 0, 1], dtype=uint8), 174: array([1, 0, 1, 0, 1, 1, 1, 0], dtype=uint8), 175: array([1, 0, 1, 0, 1, 1, 1, 1], dtype=uint8), 176: array([1, 0, 1, 1, 0, 0, 0, 0], dtype=uint8), 177: array([1, 0, 1, 1, 0, 0, 0, 1], dtype=uint8), 178: array([1, 0, 1, 1, 0, 0, 1, 0], dtype=uint8), 179: array([1, 0, 1, 1, 0, 0, 1, 1], dtype=uint8), 180: array([1, 0, 1, 1, 0, 1, 0, 0], dtype=uint8), 181: array([1, 0, 1, 1, 0, 1, 0, 1], dtype=uint8), 182: array([1, 0, 1, 1, 0, 1, 1, 0], dtype=uint8), 183: array([1, 0, 1, 1, 0, 1, 1, 1], dtype=uint8), 184: array([1, 0, 1, 1, 1, 0, 0, 0], dtype=uint8), 185: array([1, 0, 1, 1, 1, 0, 0, 1], dtype=uint8), 186: array([1, 0, 1, 1, 1, 0, 1, 0], dtype=uint8), 187: array([1, 0, 1, 1, 1, 0, 1, 1], dtype=uint8), 188: array([1, 0, 1, 1, 1, 1, 0, 0], dtype=uint8), 189: array([1, 0, 1, 1, 1, 1, 0, 1], dtype=uint8), 190: array([1, 0, 1, 1, 1, 1, 1, 0], dtype=uint8), 191: array([1, 0, 1, 1, 1, 1, 1, 1], dtype=uint8), 192: array([1, 1, 0, 0, 0, 0, 0, 0], dtype=uint8), 193: array([1, 1, 0, 0, 0, 0, 0, 1], dtype=uint8), 194: array([1, 1, 0, 0, 0, 0, 1, 0], dtype=uint8), 195: array([1, 1, 0, 0, 0, 0, 1, 1], dtype=uint8), 196: array([1, 1, 0, 0, 0, 1, 0, 0], dtype=uint8), 197: array([1, 1, 0, 0, 0, 1, 0, 1], dtype=uint8), 198: array([1, 1, 0, 0, 0, 1, 1, 0], dtype=uint8), 199: array([1, 1, 0, 0, 0, 1, 1, 1], dtype=uint8), 200: array([1, 1, 0, 0, 1, 0, 0, 0], dtype=uint8), 201: array([1, 1, 0, 0, 1, 0, 0, 1], dtype=uint8), 202: array([1, 1, 0, 0, 1, 0, 1, 0], dtype=uint8), 203: array([1, 1, 0, 0, 1, 0, 1, 1], dtype=uint8), 204: array([1, 1, 0, 0, 1, 1, 0, 0], dtype=uint8), 205: array([1, 1, 0, 0, 1, 1, 0, 1], dtype=uint8), 206: array([1, 1, 0, 0, 1, 1, 1, 0], dtype=uint8), 207: array([1, 1, 0, 0, 1, 1, 1, 1], dtype=uint8), 208: array([1, 1, 0, 1, 0, 0, 0, 0], dtype=uint8), 209: array([1, 1, 0, 1, 0, 0, 0, 1], dtype=uint8), 210: array([1, 1, 0, 1, 0, 0, 1, 0], dtype=uint8), 211: array([1, 1, 0, 1, 0, 0, 1, 1], dtype=uint8), 212: array([1, 1, 0, 1, 0, 1, 0, 0], dtype=uint8), 213: array([1, 1, 0, 1, 0, 1, 0, 1], dtype=uint8), 214: array([1, 1, 0, 1, 0, 1, 1, 0], dtype=uint8), 215: array([1, 1, 0, 1, 0, 1, 1, 1], dtype=uint8), 216: array([1, 1, 0, 1, 1, 0, 0, 0], dtype=uint8), 217: array([1, 1, 0, 1, 1, 0, 0, 1], dtype=uint8), 218: array([1, 1, 0, 1, 1, 0, 1, 0], dtype=uint8), 219: array([1, 1, 0, 1, 1, 0, 1, 1], dtype=uint8), 220: array([1, 1, 0, 1, 1, 1, 0, 0], dtype=uint8), 221: array([1, 1, 0, 1, 1, 1, 0, 1], dtype=uint8), 222: array([1, 1, 0, 1, 1, 1, 1, 0], dtype=uint8), 223: array([1, 1, 0, 1, 1, 1, 1, 1], dtype=uint8), 224: array([1, 1, 1, 0, 0, 0, 0, 0], dtype=uint8), 225: array([1, 1, 1, 0, 0, 0, 0, 1], dtype=uint8), 226: array([1, 1, 1, 0, 0, 0, 1, 0], dtype=uint8), 227: array([1, 1, 1, 0, 0, 0, 1, 1], dtype=uint8), 228: array([1, 1, 1, 0, 0, 1, 0, 0], dtype=uint8), 229: array([1, 1, 1, 0, 0, 1, 0, 1], dtype=uint8), 230: array([1, 1, 1, 0, 0, 1, 1, 0], dtype=uint8), 231: array([1, 1, 1, 0, 0, 1, 1, 1], dtype=uint8), 232: array([1, 1, 1, 0, 1, 0, 0, 0], dtype=uint8), 233: array([1, 1, 1, 0, 1, 0, 0, 1], dtype=uint8), 234: array([1, 1, 1, 0, 1, 0, 1, 0], dtype=uint8), 235: array([1, 1, 1, 0, 1, 0, 1, 1], dtype=uint8), 236: array([1, 1, 1, 0, 1, 1, 0, 0], dtype=uint8), 237: array([1, 1, 1, 0, 1, 1, 0, 1], dtype=uint8), 238: array([1, 1, 1, 0, 1, 1, 1, 0], dtype=uint8), 239: array([1, 1, 1, 0, 1, 1, 1, 1], dtype=uint8), 240: array([1, 1, 1, 1, 0, 0, 0, 0], dtype=uint8), 241: array([1, 1, 1, 1, 0, 0, 0, 1], dtype=uint8), 242: array([1, 1, 1, 1, 0, 0, 1, 0], dtype=uint8), 243: array([1, 1, 1, 1, 0, 0, 1, 1], dtype=uint8), 244: array([1, 1, 1, 1, 0, 1, 0, 0], dtype=uint8), 245: array([1, 1, 1, 1, 0, 1, 0, 1], dtype=uint8), 246: array([1, 1, 1, 1, 0, 1, 1, 0], dtype=uint8), 247: array([1, 1, 1, 1, 0, 1, 1, 1], dtype=uint8), 248: array([1, 1, 1, 1, 1, 0, 0, 0], dtype=uint8), 249: array([1, 1, 1, 1, 1, 0, 0, 1], dtype=uint8), 250: array([1, 1, 1, 1, 1, 0, 1, 0], dtype=uint8), 251: array([1, 1, 1, 1, 1, 0, 1, 1], dtype=uint8), 252: array([1, 1, 1, 1, 1, 1, 0, 0], dtype=uint8), 253: array([1, 1, 1, 1, 1, 1, 0, 1], dtype=uint8), 254: array([1, 1, 1, 1, 1, 1, 1, 0], dtype=uint8), 255: array([1, 1, 1, 1, 1, 1, 1, 1], dtype=uint8)}
Error:[3.45638663]
Pred:[0 0 0 0 0 0 0 1]
True:[0 1 0 0 0 1 0 1]
9 + 60 = 1
------------
Error:[3.63389116]
Pred:[1 1 1 1 1 1 1 1]
True:[0 0 1 1 1 1 1 1]
28 + 35 = 255
------------
Error:[3.91366595]
Pred:[0 1 0 0 1 0 0 0]
True:[1 0 1 0 0 0 0 0]
116 + 44 = 72
------------
Error:[3.72191702]
Pred:[1 1 0 1 1 1 1 1]
True:[0 1 0 0 1 1 0 1]
4 + 73 = 223
------------
Error:[3.5852713]
Pred:[0 0 0 0 1 0 0 0]
True:[0 1 0 1 0 0 1 0]
71 + 11 = 8
------------
Error:[2.53352328]
Pred:[1 0 1 0 0 0 1 0]
True:[1 1 0 0 0 0 1 0]
81 + 113 = 162
------------
Error:[0.57691441]
Pred:[0 1 0 1 0 0 0 1]
True:[0 1 0 1 0 0 0 1]
81 + 0 = 81
------------
Error:[1.42589952]
Pred:[1 0 0 0 0 0 0 1]
True:[1 0 0 0 0 0 0 1]
4 + 125 = 129
------------
Error:[0.47477457]
Pred:[0 0 1 1 1 0 0 0]
True:[0 0 1 1 1 0 0 0]
39 + 17 = 56
------------
Error:[0.21595037]
Pred:[0 0 0 0 1 1 1 0]
True:[0 0 0 0 1 1 1 0]
11 + 3 = 14
------------

5. 实现“Character-Level Language Models”源代码（必做）

在这里插入图片描述

import torch
 
# 使用RNN 有嵌入层和线性层
num_class = 4  # 4个类别
input_size = 4  # 输入维度是4
hidden_size = 8  # 隐层是8个维度
embedding_size = 10  # 嵌入到10维空间
batch_size = 1
num_layers = 2  # 两层的RNN
seq_len = 5  # 序列长度是5
 
# 准备数据
idx2char = ['e', 'h', 'l', 'o']  # 字典
x_data = [[1, 0, 2, 2, 3]]  # hello  维度（batch,seqlen）
y_data = [3, 1, 2, 3, 2]  # ohlol    维度 (batch*seqlen)
 
inputs = torch.LongTensor(x_data)
labels = torch.LongTensor(y_data)
 
 
# 构造模型
class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.emb = torch.nn.Embedding(input_size, embedding_size)
        self.rnn = torch.nn.RNN(input_size=embedding_size, hidden_size=hidden_size, num_layers=num_layers,
                                batch_first=True)
        self.fc = torch.nn.Linear(hidden_size, num_class)
 
    def forward(self, x):
        hidden = torch.zeros(num_layers, x.size(0), hidden_size)
        x = self.emb(x)  # (batch,seqlen,embeddingsize)
        x, _ = self.rnn(x, hidden)
        x = self.fc(x)
        return x.view(-1, num_class)  # 转变维2维矩阵，seq*batchsize*numclass -》((seq*batchsize),numclass)
 
 
model = Model()
 
# 损失函数和优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.05)  # lr = 0.01学习的太慢
 
# 训练
for epoch in range(15):
    optimizer.zero_grad()
    outputs = model(inputs)  # inputs是（seq,Batchsize,Inputsize） outputs是(seq,Batchsize,Hiddensize)
    loss = criterion(outputs, labels)  # labels是（seq，batchsize，1）
    loss.backward()
    optimizer.step()
 
    _, idx = outputs.max(dim=1)
    idx = idx.data.numpy()
    print("Predicted:", ''.join([idx2char[x] for x in idx]), end='')
    print(",Epoch {}/15 loss={:.3f}".format(epoch + 1, loss.item()))

实验结果：

Predicted: eeeel,Epoch 1/15 loss=1.444
Predicted: oolll,Epoch 2/15 loss=1.172
Predicted: oolol,Epoch 3/15 loss=0.926
Predicted: oolol,Epoch 4/15 loss=0.695
Predicted: ohlol,Epoch 5/15 loss=0.510
Predicted: ohlol,Epoch 6/15 loss=0.360
Predicted: ohlol,Epoch 7/15 loss=0.247
Predicted: ohlol,Epoch 8/15 loss=0.166
Predicted: ohlol,Epoch 9/15 loss=0.109
Predicted: ohlol,Epoch 10/15 loss=0.072
Predicted: ohlol,Epoch 11/15 loss=0.048
Predicted: ohlol,Epoch 12/15 loss=0.032
Predicted: ohlol,Epoch 13/15 loss=0.022
Predicted: ohlol,Epoch 14/15 loss=0.016
Predicted: ohlol,Epoch 15/15 loss=0.012

翻译Character-Level Language Models 相关内容：
Okay, so we have an idea about what RNNs are, why they are super exciting, and how they work. We’ll now ground this in a fun application: We’ll train RNN character-level language models. That is, we’ll give the RNN a huge chunk of text and ask it to model the probability distribution of the next character in the sequence given a sequence of previous characters. This will then allow us to generate new text one character at a time.
As a working example, suppose we only had a vocabulary of four possible letters “helo”, and wanted to train an RNN on the training sequence “hello”. This training sequence is in fact a source of 4 separate training examples: 1. The probability of “e” should be likely given the context of “h”, 2. “l” should be likely in the context of “he”, 3. “l” should also be likely given the context of “hel”, and finally 4. “o” should be likely given the context of “hell”.
For example, we see that in the first time step when the RNN saw the character “h” it assigned confidence of 1.0 to the next letter being “h”, 2.2 to letter “e”, -3.0 to “l”, and 4.1 to “o”. Since in our training data (the string “hello”) the next correct character is “e”, we would like to increase its confidence (green) and decrease the confidence of all other letters (red). Similarly, we have a desired target character at every one of the 4 time steps that we’d like the network to assign a greater confidence to. Since the RNN consists entirely of differentiable operations we can run the backpropagation algorithm (this is just a recursive application of the chain rule from calculus) to figure out in what direction we should adjust every one of its weights to increase the scores of the correct targets (green bold numbers). We can then perform a parameter update, which nudges every weight a tiny amount in this gradient direction. If we were to feed the same inputs to the RNN after the parameter update we would find that the scores of the correct characters (e.g. “e” in the first time step) would be slightly higher (e.g. 2.3 instead of 2.2), and the scores of incorrect characters would be slightly lower. We then repeat this process over and over many times until the network converges and its predictions are eventually consistent with the training data in that correct characters are always predicted next.
A more technical explanation is that we use the standard Softmax classifier (also commonly referred to as the cross-entropy loss) on every output vector simultaneously. The RNN is trained with mini-batch Stochastic Gradient Descent and I like to use RMSProp or Adam (per-parameter adaptive learning rate methods) to stablilize the updates.
Notice also that the first time the character “l” is input, the target is “l”, but the second time the target is “o”. The RNN therefore cannot rely on the input alone and must use its recurrent connection to keep track of the context to achieve this task.
好了，我们对rnn是什么，为什么它们超级令人兴奋，以及它们是如何工作的有了一个概念。我们现在将在一个有趣的应用程序中实现这一点:我们将训练RNN字符级语言模型。也就是说，我们将给RNN一大块文本，并要求它在给定一系列先前字符的情况下，对序列中下一个字符的概率分布进行建模。这将允许我们一次生成一个字符的新文本。
我们举一个例子，我们有一个单词是helo，并且想要训练一个RNN模型寻连hello，这个训练的序列是由四个单独的训练例子担任的，第一个字母e应该由h来给出，l应该由he来给出，l应该由hel来给出，最后一个o应该由hell给出。
例如，我们看到，在第一个时间步骤中，当RNN看到字符“h”时，它将置信度1.0分配给下一个字母“h”，2.2分配给字母“e”，-3.0分配给“l”，4.1分配给“o”。由于在我们的训练数据(字符串“hello”)中，下一个正确的字符是“e”，我们希望增加它的置信度(绿色)并降低所有其他字母(红色)的置信度。类似地，我们在4个时间步中的每一步都有一个期望的目标角色，我们希望网络对其赋予更大的置信度。由于RNN完全由可微分运算组成，我们可以运行反向传播算法(这只是微积分中链式法则的递归应用)来计算出我们应该在哪个方向调整其每一个权重，以增加正确目标的分数(绿色粗体数字)。然后，我们可以执行参数更新，在这个梯度方向上轻微推动每个权重。如果我们在参数更新后向RNN输入相同的输入，我们会发现正确字符的分数(例如第一时间步中的“e”)会稍微高一些(例如2.3而不是2.2)，而不正确字符的分数会稍微低一些。然后，我们一遍又一遍地重复这个过程，直到网络收敛，其预测最终与训练数据一致，因为接下来总是预测正确的字符。
更技术性的解释是，我们同时对每个输出向量使用标准的Softmax分类器(通常也称为交叉熵损失)。RNN训练有素的小批量随机梯度下降，我喜欢使用RMSProp或者Adam(每参数自适应学习率方法)来稳定更新。
还要注意，第一次输入字符“l”时，目标是“l”，但第二次输入时，目标是“o”。因此，RNN不能仅依赖输入，而必须使用其经常性连接来跟踪上下文以完成该任务。

7. “编码器-解码器”的简单实现（必做）

在这里插入图片描述

import torch
import numpy as np
import torch.nn as nn
import torch.utils.data as Data
 
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
letter = [c for c in 'SE?abcdefghijklmnopqrstuvwxyz']
letter2idx = {n: i for i, n in enumerate(letter)}
 
seq_data = [['man', 'women'], ['black', 'white'], ['king', 'queen'], ['girl', 'boy'], ['up', 'down'], ['high', 'low']]
 
# Seq2Seq Parameter
n_step = max([max(len(i), len(j)) for i, j in seq_data])  # max_len(=5)
n_hidden = 128
n_class = len(letter2idx)  # classfication problem
batch_size = 3
 
 
def make_data(seq_data):
    enc_input_all, dec_input_all, dec_output_all = [], [], []
 
    for seq in seq_data:
        for i in range(2):
            seq[i] = seq[i] + '?' * (n_step - len(seq[i]))  # 'man??', 'women'
 
        enc_input = [letter2idx[n] for n in (seq[0] + 'E')]  # ['m', 'a', 'n', '?', '?', 'E']
        dec_input = [letter2idx[n] for n in ('S' + seq[1])]  # ['S', 'w', 'o', 'm', 'e', 'n']
        dec_output = [letter2idx[n] for n in (seq[1] + 'E')]  # ['w', 'o', 'm', 'e', 'n', 'E']
 
        enc_input_all.append(np.eye(n_class)[enc_input])
        dec_input_all.append(np.eye(n_class)[dec_input])
        dec_output_all.append(dec_output)  # not one-hot
 
    # make tensor
    return torch.Tensor(enc_input_all), torch.Tensor(dec_input_all), torch.LongTensor(dec_output_all)
 
enc_input_all, dec_input_all, dec_output_all = make_data(seq_data)
 
 
class TranslateDataSet(Data.Dataset):
    def __init__(self, enc_input_all, dec_input_all, dec_output_all):
        self.enc_input_all = enc_input_all
        self.dec_input_all = dec_input_all
        self.dec_output_all = dec_output_all
 
    def __len__(self):  # return dataset size
        return len(self.enc_input_all)
 
    def __getitem__(self, idx):
        return self.enc_input_all[idx], self.dec_input_all[idx], self.dec_output_all[idx]
 
 
loader = Data.DataLoader(TranslateDataSet(enc_input_all, dec_input_all, dec_output_all), batch_size, True)
 
 
# Model
class Seq2Seq(nn.Module):
    def __init__(self):
        super(Seq2Seq, self).__init__()
        self.encoder = nn.RNN(input_size=n_class, hidden_size=n_hidden, dropout=0.5)  # encoder
        self.decoder = nn.RNN(input_size=n_class, hidden_size=n_hidden, dropout=0.5)  # decoder
        self.fc = nn.Linear(n_hidden, n_class)
 
    def forward(self, enc_input, enc_hidden, dec_input):
        enc_input = enc_input.transpose(0, 1)  # enc_input: [n_step+1, batch_size, n_class]
        dec_input = dec_input.transpose(0, 1)  # dec_input: [n_step+1, batch_size, n_class]
 
        # h_t : [num_layers(=1) * num_directions(=1), batch_size, n_hidden]
        _, h_t = self.encoder(enc_input, enc_hidden)
        # outputs : [n_step+1, batch_size, num_directions(=1) * n_hidden(=128)]
        outputs, _ = self.decoder(dec_input, h_t)
 
        model = self.fc(outputs)  # model : [n_step+1, batch_size, n_class]
        return model
 
 
model = Seq2Seq().to(device)
criterion = nn.CrossEntropyLoss().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
 
for epoch in range(5000):
    for enc_input_batch, dec_input_batch, dec_output_batch in loader:
        # make hidden shape [num_layers * num_directions, batch_size, n_hidden]
        h_0 = torch.zeros(1, batch_size, n_hidden).to(device)
 
        (enc_input_batch, dec_intput_batch, dec_output_batch) = (
        enc_input_batch.to(device), dec_input_batch.to(device), dec_output_batch.to(device))
        # enc_input_batch : [batch_size, n_step+1, n_class]
        # dec_intput_batch : [batch_size, n_step+1, n_class]
        # dec_output_batch : [batch_size, n_step+1], not one-hot
        pred = model(enc_input_batch, h_0, dec_intput_batch)
        # pred : [n_step+1, batch_size, n_class]
        pred = pred.transpose(0, 1)  # [batch_size, n_step+1(=6), n_class]
        loss = 0
        for i in range(len(dec_output_batch)):
            # pred[i] : [n_step+1, n_class]
            # dec_output_batch[i] : [n_step+1]
            loss += criterion(pred[i], dec_output_batch[i])
        if (epoch + 1) % 1000 == 0:
            print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.6f}'.format(loss))
 
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
 
 
# Test
def translate(word):
    enc_input, dec_input, _ = make_data([[word, '?' * n_step]])
    enc_input, dec_input = enc_input.to(device), dec_input.to(device)
    # make hidden shape [num_layers * num_directions, batch_size, n_hidden]
    hidden = torch.zeros(1, 1, n_hidden).to(device)
    output = model(enc_input, hidden, dec_input)
    # output : [n_step+1, batch_size, n_class]
 
    predict = output.data.max(2, keepdim=True)[1]  # select n_class dimension
    decoded = [letter[i] for i in predict]
    translated = ''.join(decoded[:decoded.index('E')])
 
    return translated.replace('?', '')
 
print('test')
print('man ->', translate('man'))
print('mans ->', translate('mans'))
print('king ->', translate('king'))
print('black ->', translate('black'))
print('up ->', translate('up'))
print('old ->', translate('old'))
print('high ->', translate('high'))

实验结果：

Epoch: 1000 cost = 0.002630
Epoch: 1000 cost = 0.002464
Epoch: 2000 cost = 0.000522
Epoch: 2000 cost = 0.000545
Epoch: 3000 cost = 0.000170
Epoch: 3000 cost = 0.000156
Epoch: 4000 cost = 0.000055
Epoch: 4000 cost = 0.000056
Epoch: 5000 cost = 0.000020
Epoch: 5000 cost = 0.000019
test
man -> women
mans -> women
king -> queen
black -> white
up -> down