莫烦pytorch（AI）整理笔记分

**

莫烦pytorch（AI）整理笔记分

**
自学以及交流学习—

#------------------------------------------------------
import torch
import numpy as np

np_data = np.arange(6).reshape((2, 3))
torch_data = torch.from_numpy(np_data)
tensor2array = torch_data.numpy()
print(
    '\nnumpy array:', np_data,          # [[0 1 2], [3 4 5]]
    '\ntorch tensor:', torch_data,      #  0  1  2 \n 3  4  5    [torch.LongTensor of size 2x3]
    '\ntensor to array:', tensor2array, # [[0 1 2], [3 4 5]]
)

# abs 绝对值计算
data = [-1, -2, 1, 2]
tensor = torch.FloatTensor(data)  # 转换成32位浮点 tensor
print(
    '\nabs',
    '\nnumpy: ', np.abs(data),          # [1 2 1 2]
    '\ntorch: ', torch.abs(tensor)      # [1 2 1 2]
)

# sin   三角函数 sin
print(
    '\nsin',
    '\nnumpy: ', np.sin(data),      # [-0.84147098 -0.90929743  0.84147098  0.90929743]
    '\ntorch: ', torch.sin(tensor)  # [-0.8415 -0.9093  0.8415  0.9093]
)

# mean  均值
print(
    '\nmean',
    '\nnumpy: ', np.mean(data),         # 0.0
    '\ntorch: ', torch.mean(tensor)     # 0.0
)

# matrix multiplication 矩阵点乘
data = [[1,2], [3,4]]
tensor = torch.FloatTensor(data)  # 转换成32位浮点 tensor

# correct method
print(
    '\nmatrix multiplication (matmul)',
    '\nnumpy: ', np.matmul(data, data),     # [[7, 10], [15, 22]]
    '\ntorch: ', torch.mm(tensor, tensor)   # [[7, 10], [15, 22]]
)

# !!!!  下面是错误的方法 !!!!
data = np.array(data)
print(
    '\nmatrix multiplication (dot)',
    '\nnumpy: ', data.dot(data),        # [[7, 10], [15, 22]] 在numpy 中可行
    '\ntorch: ', tensor.dot(tensor)     # torch 会转换成 [1,2,3,4].dot([1,2,3,4) = 30.0
)


tensor.dot(tensor)     # torch 会转换成 [1,2,3,4].dot([1,2,3,4) = 30.0

# 变为
torch.dot(tensor.dot(tensor)


# 什么是 Variable#------------------------------------------------------

import torch
from torch.autograd import Variable # torch 中 Variable 模块

# 先生鸡蛋
tensor = torch.FloatTensor([[1,2],[3,4]])
# 把鸡蛋放到篮子里, requires_grad是参不参与误差反向传播, 要不要计算梯度
variable = Variable(tensor, requires_grad=True)

print(tensor)
"""
 1  2
 3  4
[torch.FloatTensor of size 2x2]
"""

print(variable)
"""
Variable containing:
 1  2
 3  4
[torch.FloatTensor of size 2x2]
"""

# Variable 计算, 梯度
t_out = torch.mean(tensor*tensor)       # x^2
v_out = torch.mean(variable*variable)   # x^2
print(t_out)
print(v_out)    # 7.5


v_out.backward()    # 模拟 v_out 的误差反向传递

# 下面两步看不懂没关系, 只要知道 Variable 是计算图的一部分, 可以用来传递误差就好.
# v_out = 1/4 * sum(variable*variable) 这是计算图中的 v_out 计算步骤
# 针对于 v_out 的梯度就是, d(v_out)/d(variable) = 1/4*2*variable = variable/2

print(variable.grad)    # 初始 Variable 的梯度
'''
 0.5000  1.0000
 1.5000  2.0000
'''

# 直接print(variable)只会输出 Variable 形式的数据, 在很多时候是用不了的(比如想要用 plt 画图), 所以我们要转换一下, 将它变成 tensor 形式.

print(variable)     #  Variable 形式
"""
Variable containing:
 1  2
 3  4
[torch.FloatTensor of size 2x2]
"""

print(variable.data)    # tensor 形式
"""
 1  2
 3  4
[torch.FloatTensor of size 2x2]
"""

print(variable.data.numpy())    # numpy 形式
"""
[[ 1.  2.]
 [ 3.  4.]]
"""



# Torch 中的激励函数#------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
"""
import torch
import torch.nn.functional as F  # 激励函数都在这
from torch.autograd import Variable
import matplotlib.pyplot as plt

# fake data # 做一些假数据来观看图像
x = torch.linspace(-5, 5, 200)  # x data (tensor), shape=(100, 1)
x = Variable(x)

x_np = x.data.numpy()   # numpy array for plotting # 换成 numpy array, 出图时用

# following are popular activation functions
# 几种常用的 激励函数
y_relu = torch.relu(x).data.numpy()  # --------relu(x)
y_sigmoid = torch.sigmoid(x).data.numpy()#--sigmoid(x)
y_tanh = torch.tanh(x).data.numpy() #----------tanh(x)
y_softplus = F.softplus(x).data.numpy() # there's no softplus in torch
# y_softmax = F.softmax(x)  softmax 比较特殊, 不能直接显示, 不过他是关于概率的, 用于分类

# plt to visualize these activation function
plt.figure(1, figsize=(8, 6))

plt.subplot(221)
plt.plot(x_np, y_relu, c='red', label='relu')
plt.ylim((-1, 5))
plt.legend(loc='best')

plt.subplot(222)
plt.plot(x_np, y_sigmoid, c='red', label='sigmoid')
plt.ylim((-0.2, 1.2))
plt.legend(loc='best')

plt.subplot(223)
plt.plot(x_np, y_tanh, c='red', label='tanh')
plt.ylim((-1.2, 1.2))
plt.legend(loc='best')

plt.subplot(224)
plt.plot(x_np, y_softplus, c='red', label='softplus')
plt.ylim((-0.2, 6))
plt.legend(loc='best')

plt.show()

# 关系拟合 (回归)#------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
"""

import torch
import torch.nn.functional as F
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible
# 1d --> 2d
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size())                 # noisy y data (tensor), shape=(100, 1)

# torch can only train on Variable, so convert them to Variable
# The code below is deprecated in Pytorch 0.4. Now, autograd directly supports tensors
# x, y = Variable(x), Variable(y)

# plt.scatter(x.data.numpy(), y.data.numpy())
# plt.show()

import torch
import torch.nn.functional as F     # 激励函数都在这

class Net(torch.nn.Module):  # 继承 torch 的 Module
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()     # 继承 __init__ 功能  # 官方操作
        # 定义每层用什么样的形式
        self.hidden = torch.nn.Linear(n_feature, n_hidden)   # 隐藏层线性输出
        self.predict = torch.nn.Linear(n_hidden, n_output)   # 输出层线性输出

    def forward(self, x):   # 这同时也是 Module 中的 forward 功能
        # 正向传播输入值, 神经网络分析出输出值
        x = F.relu(self.hidden(x))      # 激励函数(隐藏层的线性值)
        x = self.predict(x)             # 输出值
        return x

net = Net(n_feature=1, n_hidden=10, n_output=1)

print(net)  # net 的结构
"""
Net (
  (hidden): Linear (1 -> 10)
  (predict): Linear (10 -> 1)
)
"""

# optimizer 是训练的工具
optimizer = torch.optim.SGD(net.parameters(), lr=0.2)  # 传入 net 的所有参数, 学习率
loss_func = torch.nn.MSELoss()      # 预测值和真实值的误差计算公式 (均方差)

plt.ion()   # something about plotting

for t in range(100):
    prediction = net(x)     # 喂给 net 训练数据 x, 输出预测值

    loss = loss_func(prediction, y)     # 计算两者的误差
    #预测值在前，真实值在后

    optimizer.zero_grad()   # 清空上一步的残余更新参数值
    loss.backward()         # 误差反向传播, 计算参数更新值
    optimizer.step()        # 将参数更新值施加到 net 的 parameters 上


    if t % 5 == 0:
        # plot and show learning process
        plt.cla()
        plt.scatter(x.data.numpy(), y.data.numpy())
        plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
        plt.text(0.5, 0, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color':  'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()


# 区分类型 (分类)#------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
"""

import torch
import matplotlib.pyplot as plt

# 假数据
n_data = torch.ones(100, 2)         # 数据的基本形态
                                    # torch.normal(means, std, out=None)####
x0 = torch.normal(2*n_data, 1)      # 类型0 x data (tensor), shape=(100, 2)
y0 = torch.zeros(100)               # 类型0 y data (tensor), shape=(100, )
x1 = torch.normal(-2*n_data, 1)     # 类型1 x data (tensor), shape=(100, 1)
y1 = torch.ones(100)                # 类型1 y data (tensor), shape=(100, )

# 注意 x, y 数据的数据形式是一定要像下面一样 (torch.cat 是在合并数据)
x = torch.cat((x0, x1), 0).type(torch.FloatTensor)  # FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)    # LongTensor = 64-bit integer

# # The code below is deprecated in Pytorch 0.4. Now, autograd directly supports tensors
# x, y = Variable(x), Variable(y)

# plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=y.data.numpy(), s=100, lw=0, cmap='RdYlGn')
# plt.show()

import torch
import torch.nn.functional as F     # 激励函数都在这

class Net(torch.nn.Module):     # 继承 torch 的 Module
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()     # 继承 __init__ 功能
        self.hidden = torch.nn.Linear(n_feature, n_hidden)   # 隐藏层线性输出
        self.out = torch.nn.Linear(n_hidden, n_output)       # 输出层线性输出

    def forward(self, x):
        # 正向传播输入值, 神经网络分析出输出值
        x = F.relu(self.hidden(x))      # 激励函数(隐藏层的线性值)
        x = self.out(x)                 # 输出值, 但是这个不是预测值, 预测值还需要再另外计算
        return x

net = Net(n_feature=2, n_hidden=10, n_output=2) # 几个类别就几个 output

# [0,1]->1
# [1,0]->0

print(net)  # net 的结构
"""
Net (
  (hidden): Linear (2 -> 10)
  (out): Linear (10 -> 2)
)
"""
# optimizer 是训练的工具
optimizer = torch.optim.SGD(net.parameters(), lr=0.02)  # 传入 net 的所有参数, 学习率
# 算误差的时候, 注意真实值!不是! one-hot 形式的, 而是1D Tensor, (batch,)
# 但是预测值是2D tensor (batch, n_classes)
loss_func = torch.nn.CrossEntropyLoss() #计算的softmax，一个概率[0.1，0.2，0.7]

for t in range(100):
    out = net(x)     # 喂给 net 训练数据 x, 输出分析值

    loss = loss_func(out, y)     # 计算两者的误差

    optimizer.zero_grad()   # 清空上一步的残余更新参数值
    loss.backward()         # 误差反向传播, 计算参数更新值
    optimizer.step()        # 将参数更新值施加到 net 的 parameters 上

    if t % 2 == 0:
        # plot and show learning process
        plt.cla()
        prediction = torch.max(out, 1)[1]
        pred_y = prediction.data.numpy()
        target_y = y.data.numpy()
        plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=pred_y, s=100, lw=0, cmap='RdYlGn')
        accuracy = float((pred_y == target_y).astype(int).sum()) / float(target_y.size)
        plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color':  'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()


# 快速搭建法 #------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.1.11
"""
import torch
import torch.nn.functional as F

# replace following class code with an easy sequential network : net2
class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_feature, n_hidden)   # hidden layer
        self.predict = torch.nn.Linear(n_hidden, n_output)   # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))      # activation function for hidden layer,小写relu
        x = self.predict(x)             # linear output
        return x

net1 = Net(1, 10, 1)

# easy and fast way to build your network #-----
net2 = torch.nn.Sequential(
    torch.nn.Linear(1, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 1)
)

print(net1)     # net1 architecture
"""
Net (
  (hidden): Linear (1 -> 10)
  (predict): Linear (10 -> 1)
)
"""

print(net2)     # net2 architecture
"""
Sequential (
  (0): Linear (1 -> 10)
  (1): ReLU ()
  (2): Linear (10 -> 1)
)
"""

# 保存提取 #------------------------------------------------------
#------------------------------------------------------#------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
"""
import torch
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

# 假数据
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size())  # noisy y data (tensor), shape=(100, 1)

def save():
    # 建网络
    net1 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )
    optimizer = torch.optim.SGD(net1.parameters(), lr=0.5)
    loss_func = torch.nn.MSELoss()

    # 训练
    for t in range(100):
        prediction = net1(x)
        loss = loss_func(prediction, y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    # plot result
    plt.figure(1, figsize=(10, 3))

    plt.subplot(131)
    plt.title('Net1')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)

    # 2 ways to save the net
    torch.save(net1, 'net.pkl')  # 保存整个网络
    torch.save(net1.state_dict(), 'net_params.pkl')  # 只保存网络中的参数 (速度快, 占内存少)

def restore_net(): #提取神经网络
    # restore entire net1 to net2
    net2 = torch.load('net.pkl')
    prediction = net2(x)

    # plot result
    plt.subplot(132)
    plt.title('Net2')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)


def restore_params(): #提取神经网络参数
    # restore only the parameters in net1 to net3，建立一个完全一样的网络
    # 新建 net3

    net3 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )

    # copy net1's parameters into net3 # 将保存的参数复制到 net3
    net3.load_state_dict(torch.load('net_params.pkl'))
    prediction = net3(x)

    # plot result
    plt.subplot(133)
    plt.title('Net3')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)

    plt.show()

# 保存 net1 (1. 整个网络, 2. 只有参数)
save()

# 提取整个网络
restore_net()

# 提取网络参数, 复制到新网络
restore_params()

# 这样我们就能看出三个网络完全一模一样啦.


# 批训练 #------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.1.11
"""
import torch
import torch.utils.data as Data
torch.manual_seed(1)    # reproducible

BATCH_SIZE = 5      # 批训练的数据个数

x = torch.linspace(1, 10, 10)       # x data (torch tensor)
# tensor([ 1.,  2.,  3.,  4.,  5.,  6.,  7.,  8.,  9., 10.])
y = torch.linspace(10, 1, 10)       # y data (torch tensor)
# tensor([10.,  9.,  8.,  7.,  6.,  5.,  4.,  3.,  2.,  1.])

# 先转换成 torch 能识别的 Dataset
torch_dataset = Data.TensorDataset(x,y)  # 将X，y对应匹配上(tensor(1.), tensor(10.))

# 把 dataset 放入 DataLoader
loader = Data.DataLoader(
    dataset=torch_dataset,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # mini batch size
    shuffle=True,               # 要不要打乱数据 (打乱比较好)
    num_workers=2,              # 多线程来读数据
)


def show_batch():
    for epoch in range(3):   # 训练所有!整套!数据 3 次
        for step, (batch_x, batch_y) in enumerate(loader):   # 每一步 loader 释放一小批数据用来学习
            # 假设这里就是你训练的地方...
            # 打出来一些数据
            print('Epoch: ', epoch, '| Step: ', step, '| batch x: ',
                  batch_x.numpy(), '| batch y: ', batch_y.numpy())



if __name__ == '__main__':
    show_batch()

"""
Epoch:  0 | Step:  0 | batch x:  [ 6.  7.  2.  3.  1.] | batch y:  [  5.   4.   9.   8.  10.]
Epoch:  0 | Step:  1 | batch x:  [  9.  10.   4.   8.   5.] | batch y:  [ 2.  1.  7.  3.  6.]
Epoch:  1 | Step:  0 | batch x:  [  3.   4.   2.   9.  10.] | batch y:  [ 8.  7.  9.  2.  1.]
Epoch:  1 | Step:  1 | batch x:  [ 1.  7.  8.  5.  6.] | batch y:  [ 10.   4.   3.   6.   5.]
Epoch:  2 | Step:  0 | batch x:  [ 3.  9.  2.  6.  7.] | batch y:  [ 8.  2.  9.  5.  4.]
Epoch:  2 | Step:  1 | batch x:  [ 10.   4.   8.   1.   5.] | batch y:  [  1.   7.   3.  10.   6.]
"""

# Optimizer 优化器 #------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
"""
import torch
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

# fake dataset
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))

# plot dataset
plt.scatter(x.numpy(), y.numpy())
plt.show()

# put dateset into torch dataset #batch
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)


# default network
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(1, 20)   # hidden layer
        self.predict = torch.nn.Linear(20, 1)   # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))      # activation function for hidden layer
        x = self.predict(x)             # linear output
        return x

if __name__ == '__main__':
    # different nets
    net_SGD         = Net()
    net_Momentum    = Net()
    net_RMSprop     = Net()
    net_Adam        = Net()
    nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]

    # different optimizers
    opt_SGD         = torch.optim.SGD(net_SGD.parameters(), lr=LR)
    opt_Momentum    = torch.optim.SGD(net_Momentum.parameters(), lr=LR, momentum=0.8)
    opt_RMSprop     = torch.optim.RMSprop(net_RMSprop.parameters(), lr=LR, alpha=0.9)
    opt_Adam        = torch.optim.Adam(net_Adam.parameters(), lr=LR, betas=(0.9, 0.99))
    optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]

    loss_func = torch.nn.MSELoss()
    losses_his = [[], [], [], []]   # record loss

    # training
    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        for step, (b_x, b_y) in enumerate(loader):          # for each training step
            for net, opt, l_his in zip(nets, optimizers, losses_his):
                output = net(b_x)              # get output for every net
                loss = loss_func(output, b_y)  # compute loss for every net

                opt.zero_grad()                # clear gradients for next train
                loss.backward()                # backpropagation, compute gradients
                opt.step()                     # apply gradients

                l_his.append(loss.data.numpy())     # loss recoder

    labels = ['SGD', 'Momentum', 'RMSprop', 'Adam']
    for i, l_his in enumerate(losses_his):
        plt.plot(l_his, label=labels[i])
    plt.legend(loc='best')
    plt.xlabel('Steps')
    plt.ylabel('Loss')
    plt.ylim((0, 0.2))
    plt.show()


# CNN 卷积神经网络 #------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
torchvision
matplotlib
"""
# library
# standard library
import os

# third-party library
import torch
import torch.nn as nn ##########
import torch.utils.data as Data
import torchvision # 数据库模块
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 1           # 训练整批数据多少次, 为了节约时间, 我们只训练一次
BATCH_SIZE = 50
LR = 0.001          # 学习率
DOWNLOAD_MNIST = False  # 如果你已经下载好了mnist数据就写上 False

# Mnist digits dataset
if not(os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
    # not mnist dir or mnist is empyt dir
    DOWNLOAD_MNIST = True
    

# Mnist 手写数字
train_data = torchvision.datasets.MNIST(
    root='./mnist/',    # 保存或者提取位置
    train=True,  # this is training data
    transform=torchvision.transforms.ToTensor(),    # 转换 PIL.Image or numpy.ndarray 成
                                                    # torch.FloatTensor (C x H x W), 训练的时候 normalize 成 [0.0, 1.0] 区间
    download=DOWNLOAD_MNIST,          # 没下载就下载, 下载了就不用再下了
)


# plot one example
print(train_data.train_data.size())                 # (60000, 28, 28)
print(train_data.train_labels.size())               # (60000)

plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()

# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
# 批训练 50 samples, 1 channel, 28x28 (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)

# 为了节约时间, 我们测试时只测试前2000个
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.
# shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1),压缩一下
test_y = test_data.test_labels[:2000]


class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(  # input shape (1, 28, 28)
            nn.Conv2d(
                in_channels=1,      # input height
                out_channels=16,    # n_filters
                kernel_size=5,      # filter size
                stride=1,           # filter movement/step
                padding=2,      # 如果想要 con2d 出来的图片长宽没有变化, padding=(kernel_size-1)/2 当 stride=1
            ),      # output shape (16, 28, 28)
            nn.ReLU(),    # activation
            nn.MaxPool2d(kernel_size=2),    # 在 2x2 空间里向下采样, output shape (16, 14, 14)
        )
        self.conv2 = nn.Sequential(  # input shape (16, 14, 14)
            nn.Conv2d(16, 32, 5, 1, 2),  # output shape (32, 14, 14)
            nn.ReLU(),  # activation
            nn.MaxPool2d(2),  # output shape (32, 7, 7)
        )
        self.out = nn.Linear(32 * 7 * 7, 10)   # fully connected layer, output 10 classes

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)  #（batch,32,7,7)--(batch_size，channels，x，y)
        x = x.view(x.size(0), -1)   #x.size(0)指batch_size的值  # 展平 多维的卷积图成 (batch_size, 32 * 7 * 7)--(batch_size, 1568)
        output = self.out(x)
        return output

cnn = CNN()
print(cnn)  # net architecture
"""
CNN (
  (conv1): Sequential (
    (0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU ()
    (2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  )
  (conv2): Sequential (
    (0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU ()
    (2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  )
  (out): Linear (1568 -> 10)
)
"""

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()                       # the target label is not one-hotted

# following function (plot_with_labels) is for visualization, can be ignored if not interested
#-----------
from matplotlib import cm

try: from sklearn.manifold import TSNE; HAS_SK = True
except: HAS_SK = False; print('Please install sklearn for layer visualization')

def plot_with_labels(lowDWeights, labels):
    plt.cla()
    X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
    for x, y, s in zip(X, Y, labels):
        c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
    plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)

plt.ion()
#-----------
# training and testing
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):   # gives batch data, normalize x when iterate train_loader

        output = cnn(b_x)[0]            # cnn output ##原先只需要cnn(b_x) 但是现在需要用到第一个返回值##
        loss = loss_func(output, b_y)   # cross entropy loss
        optimizer.zero_grad()           # clear gradients for this training step
        loss.backward()                 # backpropagation, compute gradients
        optimizer.step()                # apply gradients

        if step % 50 == 0:
            test_output, last_layer = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.numpy()  #索引每行的最大值：
            # 在计算准确率时第一个tensor# values是不需要的，所以我们只需提取第二个tensor，并将tensor格式的数据转换成array格式。
            accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size(0))
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)
            if HAS_SK:
                # Visualization of trained flatten layer (T-SNE)
                tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)   ##########################
                plot_only = 500
                low_dim_embs = tsne.fit_transform(last_layer.data.numpy()[:plot_only, :])
                labels = test_y.numpy()[:plot_only]
                plot_with_labels(low_dim_embs, labels)
plt.ioff()

# print 10 predictions from test data
test_output, _ = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')



# RNN 循环神经网络 (分类) #------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
torchvision
"""
import torch
from torch import nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import matplotlib.pyplot as plt


# torch.manual_seed(1)    # reproducible

# Hyper Parameters
# Hyper Parameters
EPOCH = 1           # 训练整批数据多少次, 为了节约时间, 我们只训练一次
BATCH_SIZE = 64
TIME_STEP = 28      # rnn 时间步数 / 图片高度
INPUT_SIZE = 28     # rnn 每步输入值 / 图片每行像素
LR = 0.01           # learning rate
DOWNLOAD_MNIST = False  # 如果你已经下载好了mnist数据就写上 Fasle

# Mnist 手写数字
train_data = torchvision.datasets.MNIST(
    root='./mnist/',    # 保存或者提取位置
    train=True,  # this is training data
    transform=torchvision.transforms.ToTensor(),    # 转换 PIL.Image or numpy.ndarray 成
                                                    # torch.FloatTensor (C x H x W), 训练的时候 normalize 成 [0.0, 1.0] 区间
    download=DOWNLOAD_MNIST,          # 没下载就下载, 下载了就不用再下了
)

# plot one example
print(train_data.train_data.size())     # (60000, 28, 28)
print(train_data.train_labels.size())   # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()

# 批训练 50samples, 1 channel, 28x28 (50, 1, 28, 28)
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# convert test data into Variable, pick 2000 samples to speed up testing
# 为了节约时间, 我们测试时只测试前2000个
test_data = dsets.MNIST(root='./mnist/', train=False, transform=transforms.ToTensor())
test_x = test_data.test_data.type(torch.FloatTensor)[:2000]/255.   # shape (2000, 28, 28) value in range(0,1)
test_y = test_data.test_labels.numpy()[:2000]    # covert to numpy array


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.rnn = nn.LSTM(         # LSTM 效果要比 nn.RNN() 好多了
            input_size=INPUT_SIZE,  # 图片每行的数据像素点
            hidden_size=64,         # rnn hidden unit
            num_layers=1,           # 有几层 RNN layers
            batch_first=True,       # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
        )

        self.out = nn.Linear(64, 10) # 输出层

    def forward(self, x):
        # x shape (batch, time_step, input_size)--(batch,28,28)
        # r_out shape (batch, time_step, output_size)
        # h_n shape (n_layers, batch, hidden_size)   LSTM 有两个 hidden states, h_n 是分线, h_c 是主线
        # h_c shape (n_layers, batch, hidden_size)
        r_out, (h_n, h_c) = self.rnn(x, None)    # None 表示 hidden state 会用全0的 state

        # choose r_out at the last time step
        out = self.out(r_out[:, -1, :])
        return out

rnn = RNN()
print(rnn)

"""
RNN (
  (rnn): LSTM(28, 64, batch_first=True)
  (out): Linear (64 -> 10)
)
"""

optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()                       # the target label is not one-hotted

# training and testing
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):        # gives batch data
        b_x = b_x.view(-1, 28, 28)              # reshape x to (batch, time_step, input_size)

        output = rnn(b_x)                               # rnn output
        loss = loss_func(output, b_y)                   # cross entropy loss
        optimizer.zero_grad()                           # clear gradients for this training step
        loss.backward()                                 # backpropagation, compute gradients
        optimizer.step()                                # apply gradients

        if step % 50 == 0:
            test_output = rnn(test_x)                   # (samples, time_step, input_size)
            pred_y = torch.max(test_output, 1)[1].data.numpy()
            accuracy = float((pred_y == test_y).astype(int).sum()) / float(test_y.size)
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)

# print 10 predictions from test data
test_output = rnn(test_x[:10].view(-1, 28, 28))
pred_y = torch.max(test_output, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:10], 'real number')


# RNN 循环神经网络 (回归) #------------------------------------------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
numpy
"""
import torch
from torch import nn
import numpy as np
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

# Hyper Parameters
TIME_STEP = 10  # rnn time step
INPUT_SIZE = 1  # rnn input size
LR = 0.02  # learning rate

# show data
steps = np.linspace(0, np.pi * 2, 100, dtype=np.float32)  # float32 for converting torch FloatTensor
x_np = np.sin(steps)
y_np = np.cos(steps)
plt.plot(steps, y_np, 'r-', label='target (cos)')
plt.plot(steps, x_np, 'b-', label='input (sin)')
plt.legend(loc='best')
plt.show()

class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.rnn = nn.RNN(  # 这回一个普通的 RNN 就能胜任
            input_size=INPUT_SIZE,
            hidden_size=32,  # rnn hidden unit,单个隐藏节点的尺寸？
            num_layers=1,  # number of rnn layer
            batch_first=True,  # input & output 会是以 batch size 为第一维度的特征集 e.g. (batch, time_step, input_size)
        )
        self.out = nn.Linear(32, 1)

    def forward(self, x, h_state):  # 因为 hidden state 是连续的, 所以我们要一直传递这一个 state
        # x (batch, time_step, input_size)
        # h_state (n_layers, batch, hidden_size)
        # r_out (batch, time_step, hidden_size)
        r_out, h_state = self.rnn(x, h_state)  # h_state 也要作为 RNN 的一个输入

        outs = []  # 保存所有时间点的预测值
        for time_step in range(r_out.size(1)):  # 对每一个时间点计算 output
            outs.append(self.out(r_out[:, time_step, :]))
        return torch.stack(outs, dim=1), h_state

        # instead, for simplicity, you can replace above codes by follows
        # r_out = r_out.view(-1, 32)
        # outs = self.out(r_out)
        # outs = outs.view(-1, TIME_STEP, 1)
        # return outs, h_state

        # or even simpler, since nn.Linear can accept inputs of any dimension
        # and returns outputs with same dimension except for the last
        # outs = self.out(r_out)
        # return outs

rnn = RNN()
print(rnn)

"""
RNN (
  (rnn): RNN(1, 32, batch_first=True)
  (out): Linear (32 -> 1)
)
"""

optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)  # optimize all cnn parameters
loss_func = nn.MSELoss()

h_state = None  # for initial hidden state第一个hidden state

plt.figure(1, figsize=(12, 5))
plt.ion()  # continuously plot

for step in range(100):
    start, end = step * np.pi, (step + 1) * np.pi  # time range
    # use sin predicts cos
    steps = np.linspace(start, end, TIME_STEP, dtype=np.float32,
                        endpoint=False)  # float32 for converting torch FloatTensor
    x_np = np.sin(steps)
    y_np = np.cos(steps)

    x = torch.from_numpy(x_np[np.newaxis, :, np.newaxis])  # shape (batch, time_step, input_size)
    y = torch.from_numpy(y_np[np.newaxis, :, np.newaxis])

    prediction, h_state = rnn(x, h_state)  # rnn output
    # !! next step is important !!
    h_state = h_state.data  # repack the hidden state, break the connection from last iteration

    loss = loss_func(prediction, y)  # calculate loss
    optimizer.zero_grad()  # clear gradients for this training step
    loss.backward()  # backpropagation, compute gradients
    optimizer.step()  # apply gradients

    # plotting
    plt.plot(steps, y_np.flatten(), 'r-')
    plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
    plt.draw();
    plt.pause(0.05)

plt.ioff()
plt.show()

# AutoEncoder (自编码/非监督学习) (Autoencoder) #------------------#------------------#------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
numpy
"""
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
import numpy as np


# torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005         # learning rate
DOWNLOAD_MNIST = False   # 下过数据的话, 就可以设置成 False
N_TEST_IMG = 5          # 到时候显示 5张图片看效果, 如上图一

# Mnist digits dataset
train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                     # this is training data
    transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                                    # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,                        # download it if you don't have it
)
# plot one example
print(train_data.train_data.size())     # (60000, 28, 28)
print(train_data.train_labels.size())   # (60000)
plt.imshow(train_data.train_data[2].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[2])
plt.show()

# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# no testdata # ----------

class AutoEncoder(nn.Module):
    def __init__(self):
        super(AutoEncoder, self).__init__()

        self.encoder = nn.Sequential(
            nn.Linear(28*28, 128),
            nn.Tanh(),
            nn.Linear(128, 64),
            nn.Tanh(),
            nn.Linear(64, 12),
            nn.Tanh(),
            nn.Linear(12, 3),   # 压缩成3个特征, 进行 3D 图像可视化
        )
        self.decoder = nn.Sequential(
            nn.Linear(3, 12),
            nn.Tanh(),
            nn.Linear(12, 64),
            nn.Tanh(),
            nn.Linear(64, 128),
            nn.Tanh(),
            nn.Linear(128, 28*28),
            nn.Sigmoid(),       # 激励函数让输出值在 (0, 1) ####-------
        )

    def forward(self, x):
        encoded = self.encoder(x)
        decoded = self.decoder(encoded)
        return encoded, decoded

autoencoder = AutoEncoder()

optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()

# initialize figure
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion()   # continuously plot

# original data (first row) for viewing
view_data = train_data.train_data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255.
for i in range(N_TEST_IMG):
    a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray'); a[0][i].set_xticks(()); a[0][i].set_yticks(())

for epoch in range(EPOCH):
    for step, (x, b_label) in enumerate(train_loader):
        b_x = x.view(-1, 28*28)   # batch x, shape (batch, 28*28)
        b_y = x.view(-1, 28*28)   # batch y, shape (batch, 28*28)

        encoded, decoded = autoencoder(b_x)

        loss = loss_func(decoded, b_y)      # mean square error
        
        optimizer.zero_grad()               # clear gradients for this training step
        loss.backward()                     # backpropagation, compute gradients
        optimizer.step()                    # apply gradients

        if step % 100 == 0:
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy())

            # plotting decoded image (second row)
            _, decoded_data = autoencoder(view_data)
            for i in range(N_TEST_IMG):
                a[1][i].clear()
                a[1][i].imshow(np.reshape(decoded_data.data.numpy()[i], (28, 28)), cmap='gray')
                a[1][i].set_xticks(()); a[1][i].set_yticks(())
            plt.draw(); plt.pause(0.05)

plt.ioff()
plt.show()

# visualize in 3D plot
view_data = train_data.train_data[:200].view(-1, 28*28).type(torch.FloatTensor)/255.
encoded_data, _ = autoencoder(view_data)
fig = plt.figure(2); ax = Axes3D(fig)
X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()
values = train_data.train_labels[:200].numpy()
for x, y, z, s in zip(X, Y, Z, values):
    c = cm.rainbow(int(255*s/9)); ax.text(x, y, z, s, backgroundcolor=c)
ax.set_xlim(X.min(), X.max()); ax.set_ylim(Y.min(), Y.max()); ax.set_zlim(Z.min(), Z.max())
plt.show()

# DQN 强化学习#------------------#------------------#------------------
"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
More about Reinforcement learning: https://mofanpy.com/tutorials/machine-learning/reinforcement-learning/
Dependencies:
torch: 0.4
gym: 0.8.1
numpy
"""

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import gym

# 超参数
BATCH_SIZE = 32
LR = 0.01                   # learning rate
EPSILON = 0.9               # 最优选择动作百分比
GAMMA = 0.9                 # 奖励递减参数
TARGET_REPLACE_ITER = 100   # Q 现实网络的更新频率
MEMORY_CAPACITY = 2000      # 记忆库大小
env = gym.make('CartPole-v0')   # 立杆子游戏
env = env.unwrapped
N_ACTIONS = env.action_space.n  # 杆子能做的动作
N_STATES = env.observation_space.shape[0]   # 杆子能获取的环境信息数
ENV_A_SHAPE = 0 if isinstance(env.action_space.sample(), int) else env.action_space.sample().shape     # to confirm the shape


class Net(nn.Module):
    def __init__(self, ):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(N_STATES, 50)
        self.fc1.weight.data.normal_(0, 0.1)   # initialization
        self.out = nn.Linear(50, N_ACTIONS)
        self.out.weight.data.normal_(0, 0.1)   # initialization

    def forward(self, x):
        x = self.fc1(x)
        x = F.relu(x)
        actions_value = self.out(x)
        return actions_value


class DQN(object):
    def __init__(self):# 建立 target net 和 eval net 还有 memory
        self.eval_net, self.target_net = Net(), Net()

        self.learn_step_counter = 0     # 用于 target 更新计时
        self.memory_counter = 0         # 记忆库记数
        self.memory = np.zeros((MEMORY_CAPACITY, N_STATES * 2 + 2))     # 初始化记忆库
        self.optimizer = torch.optim.Adam(self.eval_net.parameters(), lr=LR)    # torch 的优化器
        self.loss_func = nn.MSELoss()   # 误差公式

    def choose_action(self, x):# 根据环境观测值选择动作的机制
        x = torch.unsqueeze(torch.FloatTensor(x), 0)
        # 这里只输入一个 sample
        if np.random.uniform() < EPSILON:   # 选最优动作
            actions_value = self.eval_net.forward(x)
            action = torch.max(actions_value, 1)[1].data.numpy()[0, 0]     # return the argmax
        else:   # 选随机动作
            action = np.random.randint(0, N_ACTIONS)
        return action

    def store_transition(self, s, a, r, s_):# 存储记忆
        transition = np.hstack((s, [a, r], s_))
        # 如果记忆库满了, 就覆盖老数据
        index = self.memory_counter % MEMORY_CAPACITY
        self.memory[index, :] = transition
        self.memory_counter += 1

    def learn(self):
        # target 网络更新
        # 学习记忆库中的记忆
        # target net 参数更新
        if self.learn_step_counter % TARGET_REPLACE_ITER == 0:
            self.target_net.load_state_dict(self.eval_net.state_dict())
        self.learn_step_counter += 1

        # 抽取记忆库中的批数据
        sample_index = np.random.choice(MEMORY_CAPACITY, BATCH_SIZE)
        b_memory = self.memory[sample_index, :]
        b_s = torch.FloatTensor(b_memory[:, :N_STATES])
        b_a = torch.LongTensor(b_memory[:, N_STATES:N_STATES+1].astype(int))
        b_r = torch.FloatTensor(b_memory[:, N_STATES+1:N_STATES+2])
        b_s_ = torch.FloatTensor(b_memory[:, -N_STATES:])

        # 针对做过的动作b_a, 来选 q_eval 的值, (q_eval 原本有所有动作的值)
        q_eval = self.eval_net(b_s).gather(1, b_a)  # shape (batch, 1)
        q_next = self.target_net(b_s_).detach()     # q_next 不进行反向传递误差, 所以 detach
        q_target = b_r + GAMMA * q_next.max(1)[0]   # shape (batch, 1)
        loss = self.loss_func(q_eval, q_target)

        # 计算, 更新 eval net
        self.optimizer.zero_grad()
        loss.backward()
        self.optimizer.step()

dqn = DQN() # 定义 DQN 系统

for i_episode in range(400):
    s = env.reset()
    while True:
        env.render()    # 显示实验动画
        a = dqn.choose_action(s)

        # 选动作, 得到环境反馈
        s_, r, done, info = env.step(a)

        # 修改 reward, 使 DQN 快速学习
        x, x_dot, theta, theta_dot = s_
        r1 = (env.x_threshold - abs(x)) / env.x_threshold - 0.8
        r2 = (env.theta_threshold_radians - abs(theta)) / env.theta_threshold_radians - 0.5
        r = r1 + r2

        # 存记忆
        dqn.store_transition(s, a, r, s_)

        if dqn.memory_counter > MEMORY_CAPACITY:
            dqn.learn() # 记忆库满了就进行学习

        if done:    # 如果回合结束, 进入下回合
            break

        s = s_



# GAN (Generative Adversarial Nets 生成对抗网络)#------------------#------------------#------------------


"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
numpy
matplotlib
"""
import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
# torch.manual_seed(1)    # reproducible
# np.random.seed(1)
# Hyper Parameters
BATCH_SIZE = 64
LR_G = 0.0001           # learning rate for generator
LR_D = 0.0001           # learning rate for discriminator
N_IDEAS = 5             # think of this as number of ideas for generating an art work (Generator)
ART_COMPONENTS = 15     # it could be total point G can draw in the canvas
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])
# show our beautiful painting range
# plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
# plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
# plt.legend(loc='upper right')
# plt.show()

def artist_works():     # painting from the famous artist (real target)
    a = np.random.uniform(1, 2, size=BATCH_SIZE)[:, np.newaxis]
    paintings = a * np.power(PAINT_POINTS, 2) + (a-1)
    paintings = torch.from_numpy(paintings).float()
    return paintings

G = nn.Sequential(                      # Generator
nn.Linear(N_IDEAS, 128),            # random ideas (could from normal distribution)
nn.ReLU(),
nn.Linear(128, ART_COMPONENTS),     # making a painting from these random ideas
)

D = nn.Sequential(                      # Discriminator
nn.Linear(ART_COMPONENTS, 128),     # receive art work either from the famous artist or a newbie like G
nn.ReLU(),
nn.Linear(128, 1),
nn.Sigmoid(),                       # tell the probability that the art work is made by artist
)

opt_D = torch.optim.Adam(D.parameters(), lr=LR_D)
opt_G = torch.optim.Adam(G.parameters(), lr=LR_G)
plt.ion()   # something about continuous plotting

for step in range(10000):
    artist_paintings = artist_works()  # real painting from artist
    G_ideas = torch.randn(BATCH_SIZE, N_IDEAS, requires_grad=True)  # random ideas\n  #（64，5）
    G_paintings = G(G_ideas)                    # fake painting from G (random ideas)
    prob_artist1 = D(G_paintings)               # D try to reduce this prob

    prob_artist0 = D(artist_paintings)          # D try to increase this prob
    prob_artist1 = D(G_paintings.detach())      # D try to reduce this prob

    D_loss = - torch.mean(torch.log(prob_artist0) + torch.log(1. - prob_artist1)) #####################----------
    G_loss = torch.mean(torch.log(1. - prob_artist1)) #################################################----------

    opt_G.zero_grad()
    G_loss.backward()
    opt_G.step()

    opt_D.zero_grad()
    D_loss.backward(retain_graph=True)          # reusing computational graph #保留网络中的参数
    opt_D.step()

if step % 50 == 0:  # plotting
    plt.cla()
    plt.plot(PAINT_POINTS[0], G_paintings.data.numpy()[0], c='#4AD631', lw=3, label='Generated painting',)
    plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
    plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
    plt.text(-.5, 2.3, 'D accuracy=%.2f (0.5 for D to converge)' % prob_artist0.data.numpy().mean(), fontdict={'size': 13})
    plt.text(-.5, 2, 'D score= %.2f (-1.38 for G to converge)' % -D_loss.data.numpy(), fontdict={'size': 13})
    plt.ylim((0, 3));plt.legend(loc='upper right', fontsize=10);plt.draw();plt.pause(0.01)
    plt.ioff()
    plt.show()


# 为什么 Torch 是动态的 #------------------#------------------#------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
numpy
"""
import torch
from torch import nn
import numpy as np
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible
# Hyper Parameters
INPUT_SIZE = 1          # rnn input size / image width
LR = 0.02               # learning rate


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.rnn = nn.RNN(
            input_size=1,
            hidden_size=32,     # rnn hidden unit
            num_layers=1,       # number of rnn layer
            batch_first=True,   # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
        )
        self.out = nn.Linear(32, 1)

    def forward(self, x, h_state):
        # x (batch, time_step, input_size)
        # h_state (n_layers, batch, hidden_size)
        # r_out (batch, time_step, output_size)
        r_out, h_state = self.rnn(x, h_state)

        outs = []                                   # this is where you can find torch is dynamic
        for time_step in range(r_out.size(1)):      # calculate output for each time step
            outs.append(self.out(r_out[:, time_step, :]))
        return torch.stack(outs, dim=1), h_state

rnn = RNN()
print(rnn)

optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.MSELoss()                                # the target label is not one-hotted

h_state = None   # for initial hidden state

plt.figure(1, figsize=(12, 5))
plt.ion()   # continuously plot

########################  Below is different #########################

################ static time steps ##########
# for step in range(60):
#     start, end = step * np.pi, (step+1)*np.pi   # time steps
#     # use sin predicts cos
#     steps = np.linspace(start, end, 10, dtype=np.float32)

################ dynamic time steps #########
step = 0
for i in range(60):
    dynamic_steps = np.random.randint(1, 4)  # has random time steps
    start, end = step * np.pi, (step + dynamic_steps) * np.pi  # different time steps length
    step += dynamic_steps

    # use sin predicts cos
    steps = np.linspace(start, end, 10 * dynamic_steps, dtype=np.float32)

#######################  Above is different ###########################

    print(len(steps))       # print how many time step feed to RNN

    x_np = np.sin(steps)    # float32 for converting torch FloatTensor
    y_np = np.cos(steps)

    x = torch.from_numpy(x_np[np.newaxis, :, np.newaxis])    # shape (batch, time_step, input_size)
    y = torch.from_numpy(y_np[np.newaxis, :, np.newaxis])

    prediction, h_state = rnn(x, h_state)   # rnn output
    # !! next step is important !!
    h_state = h_state.data        # repack the hidden state, break the connection from last iteration

    loss = loss_func(prediction, y)         # cross entropy loss
    optimizer.zero_grad()                   # clear gradients for this training step
    loss.backward()                         # backpropagation, compute gradients
    optimizer.step()                        # apply gradients

    # plotting
    plt.plot(steps, y_np.flatten(), 'r-')
    plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
    plt.draw()
    plt.pause(0.05)

plt.ioff()
plt.show()

# GPU 加速运算 #------------------#------------------#------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
torchvision
"""
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
# torch.manual_seed(1)

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(root='./mnist/', train=True, transform=torchvision.transforms.ToTensor(), download=DOWNLOAD_MNIST,)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)

# !!!!!!!! Change in here !!!!!!!!! #
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000].cuda()/255.   # Tensor on GPU
test_y = test_data.test_labels[:2000].cuda()

class CNN(nn.Module):
  def __init__(self):
        super(CNN, self).__init__()
        
        self.conv1 = nn.Sequential(nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2,),
        nn.ReLU(), nn.MaxPool2d(kernel_size=2))
        self.conv2 = nn.Sequential(nn.Conv2d(16, 32, 5, 1, 2), nn.ReLU(), nn.MaxPool2d(2),)
        self.out = nn.Linear(32 * 7 * 7, 10)
        
  def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output

cnn = CNN()
# !!!!!!!! Change in here !!!!!!!!! #
cnn.cuda()      # Moves all model parameters and buffers to the GPU.
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):
        # !!!!!!!! Change in here !!!!!!!!! #
        b_x = x.cuda()    # Tensor on GPU
        b_y = y.cuda()    # Tensor on GPU
        
        output = cnn(b_x)
        loss = loss_func(output, b_y)
        
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)
            # !!!!!!!! Change in here !!!!!!!!! #
            pred_y = torch.max(test_output, 1)[1].cuda().data  # move the computation in GPU
            accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.cpu().numpy(), '| test accuracy: %.2f' % accuracy)
            test_output = cnn(test_x[:10])
            # !!!!!!!! Change in here !!!!!!!!! #
            pred_y = torch.max(test_output, 1)[1].cuda().data # move the computation in GPU
            print(pred_y, 'prediction number')
            print(test_y[:10], 'real number')

# Dropout 缓解过拟合 #------------------#------------------#------------------

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
"""
import torch
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

N_SAMPLES = 20
N_HIDDEN = 300

# training data
x = torch.unsqueeze(torch.linspace(-1, 1, N_SAMPLES), 1)
y = x + 0.3*torch.normal(torch.zeros(N_SAMPLES, 1), torch.ones(N_SAMPLES, 1))

# test data
test_x = torch.unsqueeze(torch.linspace(-1, 1, N_SAMPLES), 1)
test_y = test_x + 0.3*torch.normal(torch.zeros(N_SAMPLES, 1), torch.ones(N_SAMPLES, 1))

# show data
plt.scatter(x.data.numpy(), y.data.numpy(), c='magenta', s=50, alpha=0.5, label='train')
plt.scatter(test_x.data.numpy(), test_y.data.numpy(), c='cyan', s=50, alpha=0.5, label='test')
plt.legend(loc='upper left')
plt.ylim((-2.5, 2.5))
plt.show()

net_overfitting = torch.nn.Sequential(
    torch.nn.Linear(1, N_HIDDEN), # N_HIDDEN = 300
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, N_HIDDEN),
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, 1),
)

net_dropped = torch.nn.Sequential(
    torch.nn.Linear(1, N_HIDDEN),
    torch.nn.Dropout(0.5),  # drop 50% of the neuron
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, N_HIDDEN),
    torch.nn.Dropout(0.5),  # drop 50% of the neuron
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, 1),
)

print(net_overfitting)  # net architecture
print(net_dropped)

optimizer_ofit = torch.optim.Adam(net_overfitting.parameters(), lr=0.01)
optimizer_drop = torch.optim.Adam(net_dropped.parameters(), lr=0.01)
loss_func = torch.nn.MSELoss()

plt.ion()   # something about plotting

for t in range(500):
    pred_ofit = net_overfitting(x)
    pred_drop = net_dropped(x)
    loss_ofit = loss_func(pred_ofit, y)
    loss_drop = loss_func(pred_drop, y)

    optimizer_ofit.zero_grad()
    optimizer_drop.zero_grad()
    loss_ofit.backward()
    loss_drop.backward()
    optimizer_ofit.step()
    optimizer_drop.step()

    if t % 10 == 0:
        # change to eval mode in order to fix drop out effect
        net_overfitting.eval() # 预测模式
        net_dropped.eval()  # parameters for dropout differ from train mode

        # plotting
        plt.cla()
        test_pred_ofit = net_overfitting(test_x)
        test_pred_drop = net_dropped(test_x)

        plt.scatter(x.data.numpy(), y.data.numpy(), c='magenta', s=50, alpha=0.3, label='train')
        plt.scatter(test_x.data.numpy(), test_y.data.numpy(), c='cyan', s=50, alpha=0.3, label='test')
        plt.plot(test_x.data.numpy(), test_pred_ofit.data.numpy(), 'r-', lw=3, label='overfitting')
        plt.plot(test_x.data.numpy(), test_pred_drop.data.numpy(), 'b--', lw=3, label='dropout(50%)')
        plt.text(0, -1.2, 'overfitting loss=%.4f' % loss_func(test_pred_ofit, test_y).data.numpy(), fontdict={'size': 20, 'color':  'red'})
        plt.text(0, -1.5, 'dropout loss=%.4f' % loss_func(test_pred_drop, test_y).data.numpy(), fontdict={'size': 20, 'color': 'blue'})
        plt.legend(loc='upper left'); plt.ylim((-2.5, 2.5));plt.pause(0.1)

        # change back to train mode
        net_overfitting.train()
        net_dropped.train()

plt.ioff()
plt.show()



# Batch Normalization 批标准化 #------------------#------------------#------------------
"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
numpy
"""
import torch
from torch import nn
from torch.nn import init
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt
import numpy as np

# 超参数
N_SAMPLES = 2000
BATCH_SIZE = 64
EPOCH = 12
LR = 0.03
N_HIDDEN = 8
ACTIVATION = F.tanh     # 你可以换 relu 试试
B_INIT = -0.2   # 模拟不好的 参数初始化

# training data
x = np.linspace(-7, 10, N_SAMPLES)[:, np.newaxis]  # np.newaxis的功能:插入新维度
noise = np.random.normal(0, 2, x.shape)
y = np.square(x) - 5 + noise

# test data
test_x = np.linspace(-7, 10, 200)[:, np.newaxis]
noise = np.random.normal(0, 2, test_x.shape)
test_y = np.square(test_x) - 5 + noise

train_x, train_y = torch.from_numpy(x).float(), torch.from_numpy(y).float()
test_x = torch.from_numpy(test_x).float()
test_y = torch.from_numpy(test_y).float()

train_dataset = Data.TensorDataset(train_x, train_y) # one to one 
train_loader = Data.DataLoader(dataset=train_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)

# show data
plt.scatter(train_x.numpy(), train_y.numpy(), c='#FF9359', s=50, alpha=0.2, label='train')
plt.legend(loc='upper left')
plt.show()


class Net(nn.Module):
    def __init__(self, batch_normalization=False):
        super(Net, self).__init__()
        
        self.do_bn = batch_normalization
        self.fcs = []   # 太多层了, 我们用 for loop 建立
        self.bns = []
        self.bn_input = nn.BatchNorm1d(1, momentum=0.5)   # 给 input 的 BN

        for i in range(N_HIDDEN):               # 建层
            input_size = 1 if i == 0 else 10
            fc = nn.Linear(input_size, 10)
            setattr(self, 'fc%i' % i, fc)       # 注意! pytorch 一定要你将层信息变成 class 的属性! 我在这里花了2天时间发现了这个 bug
            # self.fc = fc
            self._set_init(fc)                  # 参数初始化
            self.fcs.append(fc)
            if self.do_bn:
                bn = nn.BatchNorm1d(10, momentum=0.5)
                setattr(self, 'bn%i' % i, bn)   # 注意! pytorch 一定要你将层信息变成 class 的属性! 我在这里花了2天时间发现了这个 bug
                self.bns.append(bn)

        self.predict = nn.Linear(10, 1)         # output layer
        self._set_init(self.predict)            # 参数初始化

    def _set_init(self, layer):     # 参数初始化
        init.normal_(layer.weight, mean=0., std=.1)
        init.constant_(layer.bias, B_INIT)

    def forward(self, x):
        pre_activation = [x]
        if self.do_bn: x = self.bn_input(x)    # 判断是否要加 BN
        layer_input = [x]
        for i in range(N_HIDDEN):
            x = self.fcs[i](x)
            pre_activation.append(x)    # 为之后出图
            if self.do_bn: x = self.bns[i](x)  # 判断是否要加 BN
            x = ACTIVATION(x)
            layer_input.append(x)       # 为之后出图
        out = self.predict(x)
        return out, layer_input, pre_activation

# 建立两个 net, 一个有 BN, 一个没有
nets = [Net(batch_normalization=False), Net(batch_normalization=True)]

# print(*nets)    # print net architecture

opts = [torch.optim.Adam(net.parameters(), lr=LR) for net in nets]

loss_func = torch.nn.MSELoss()


def plot_histogram(l_in, l_in_bn, pre_ac, pre_ac_bn):
    for i, (ax_pa, ax_pa_bn, ax, ax_bn) in enumerate(zip(axs[0, :], axs[1, :], axs[2, :], axs[3, :])):
        [a.clear() for a in [ax_pa, ax_pa_bn, ax, ax_bn]]
        if i == 0:
            p_range = (-7, 10);the_range = (-7, 10)
        else:
            p_range = (-4, 4);the_range = (-1, 1)
        ax_pa.set_title('L' + str(i))
        ax_pa.hist(pre_ac[i].data.numpy().ravel(), bins=10, range=p_range, color='#FF9359', alpha=0.5);ax_pa_bn.hist(pre_ac_bn[i].data.numpy().ravel(), bins=10, range=p_range, color='#74BCFF', alpha=0.5)
        ax.hist(l_in[i].data.numpy().ravel(), bins=10, range=the_range, color='#FF9359');ax_bn.hist(l_in_bn[i].data.numpy().ravel(), bins=10, range=the_range, color='#74BCFF')
        for a in [ax_pa, ax, ax_pa_bn, ax_bn]: a.set_yticks(());a.set_xticks(())
        ax_pa_bn.set_xticks(p_range);ax_bn.set_xticks(the_range)
        axs[0, 0].set_ylabel('PreAct');axs[1, 0].set_ylabel('BN PreAct');axs[2, 0].set_ylabel('Act');axs[3, 0].set_ylabel('BN Act')
    plt.pause(0.01)


if __name__ == "__main__":
    f, axs = plt.subplots(4, N_HIDDEN + 1, figsize=(10, 5))
    plt.ion()  # something about plotting
    plt.show()

    # training
    losses = [[], []]  # recode loss for two networks# 每个网络一个 list 来记录误差

    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        layer_inputs, pre_acts = [], []
        for net, l in zip(nets, losses):# 训练两个网络
            net.eval()              # set eval mode to fix moving_mean and moving_var
            pred, layer_input, pre_act = net(test_x)
            l.append(loss_func(pred, test_y).data.item())
            layer_inputs.append(layer_input)
            pre_acts.append(pre_act)
            net.train()             # free moving_mean and moving_var
        plot_histogram(*layer_inputs, *pre_acts)     # plot histogram

        for step, (b_x, b_y) in enumerate(train_loader):
            for net, opt in zip(nets, opts):     # train for each network
                pred, _, _ = net(b_x)
                loss = loss_func(pred, b_y)
                opt.zero_grad()
                loss.backward()
                opt.step()    # it will also learns the parameters in Batch Normalization
                # 这也会训练 BN 里面的参数
    plt.ioff()

    # plot training loss
    plt.figure(2)
    plt.plot(losses[0], c='#FF9359', lw=3, label='Original')
    plt.plot(losses[1], c='#74BCFF', lw=3, label='Batch Normalization')
    plt.xlabel('step');plt.ylabel('test loss');plt.ylim((0, 2000));plt.legend(loc='best')

    # evaluation
    # set net to eval mode to freeze the parameters in batch normalization layers
    [net.eval() for net in nets]    # set eval mode to fix moving_mean and moving_var
    preds = [net(test_x)[0] for net in nets]
    plt.figure(3)
    plt.plot(test_x.data.numpy(), preds[0].data.numpy(), c='#FF9359', lw=4, label='Original')
    plt.plot(test_x.data.numpy(), preds[1].data.numpy(), c='#74BCFF', lw=4, label='Batch Normalization')
    plt.scatter(test_x.data.numpy(), test_y.data.numpy(), c='r', s=50, alpha=0.2, label='train')
    plt.legend(loc='best')
    plt.show()