莫烦python学习笔记

莫烦pytorch学习笔记

PyTorch是一个比较新的模块，比Tensorflow能更好地诠释神经网络的性能。

不同： Tensorflow是静态过程，PyTorch是动态过程

import torch
import numpy as np

np_data = np.arange(6).reshape((2, 3))  # 生成一个numpy数组
torch_data = torch.from_numpy(np_data)  # numpy转换成torch
tensor2array = torch_data.numpy()  # torch转换称numpy
print(
    '\nnumpy', np_data,
    '\notrch', torch_data,
    '\ntensor2array', tensor2array
)

numpy [[0 1 2]
 [3 4 5]] 
otrch tensor([[0, 1, 2],
        [3, 4, 5]], dtype=torch.int32) 
tensor2array [[0 1 2]
 [3 4 5]]

# ads绝对值
data = [-1, -2, 1, 2]
tensor = torch.FloatTensor(data)  # 转换成23bitflotpoints
# http://pytorch.org/docs/torch.html#math-operations
# 包括tensor的一些运算

print(
    '\nabs', 
    '\nnumpy: ', np.abs(data),  # numpy形式
    '\ntorch: ', torch.abs(tensor)  #torch形式
)

# 其他计算形式类似
print(
    '\nsin', 
    '\nnumpy: ', np.sin(data),  # numpy形式
    '\ntorch: ', torch.sin(tensor)  #torch形式
)

# 矩阵形式运算
data = [[1, 2], [3, 4]]
tensor = torch.FloatTensor(data)
data = np.array(data)

print(
    '\nnumpy:', np.matmul(data, data),  # 或np.dot(data)
    '\ntorch:', torch.mm(tensor, tensor)  # 不能使用torch.dot(data)
)

abs 
numpy:  [1 2 1 2] 
torch:  tensor([1., 2., 1., 2.])

sin 
numpy:  [-0.84147098 -0.90929743  0.84147098  0.90929743] 
torch:  tensor([-0.8415, -0.9093,  0.8415,  0.9093])

numpy: [[ 7 10]
 [15 22]] 
torch: tensor([[ 7., 10.],
        [15., 22.]])

import torch
from torch.autograd import Variable

tensor = torch.FloatTensor([[1, 2], [3, 4]])     # 不能反向传播
variable = Variable(tensor, requires_grad=True)  # requires_grad=True可以反向传播

print(tensor)
print(variable)  # Variable containing

t_out = torch.mean(tensor*tensor)  
v_out = torch.mean(variable*variable)

print('t_out =', t_out)
print('v_out =', v_out)

v_out.backward()
# v_out = 1/4*sum(variable*variable)
# d(v_out)/d(var) = 1/4*2*variable = variable/2
print(variable.grad)  # 输出variable的梯度

print(variable)
print(variable.data)          # variable转换成tensor
print(variable.data.numpy())  # variable转换成tensor，tensor转换成numpy的值

tensor([[1., 2.],
        [3., 4.]])
tensor([[1., 2.],
        [3., 4.]], requires_grad=True)
t_out = tensor(7.5000)
v_out = tensor(7.5000, grad_fn=)
tensor([[0.5000, 1.0000],
        [1.5000, 2.0000]])
tensor([[1., 2.],
        [3., 4.]], requires_grad=True)
tensor([[1., 2.],
        [3., 4.]])
[[1. 2.]
 [3. 4.]]

# 激励函数Activation function
# 卷积神经网络：推荐relu
# 循环神经网络：推荐relu or tanh

import torch
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt

# fake data
x = torch.linspace(-5, 5, 200)  # x data (tensor), shape=(100, 1)
x = Variable(x)  # 将x装到Variable这个篮子里面，x变成variable
x_np = x.data.numpy()  # torch的数据格式不能被matplotlib识别，转换成numpy

y_relu = F.relu(x).data.numpy()
y_sigmoid = F.sigmoid(x).data.numpy()
y_tanh = F.tanh(x).data.numpy()
y_softplus = F.softplus(x).data.numpy()
# y_softmax = F.relu(x).data.numpy()

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='upper left')

# 回归
import torch
import torch.nn.functional as F     # 激励函数都在这
import matplotlib.pyplot as plt
from torch.autograd import Variable

# 生成一些随机点
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # 把一维的数据变成二维的数据
y = x.pow(2) + 0.2 * torch.rand(x.size())  # x的平方，加上一点噪声的影响。
# torch.rand(x.size())是随机生(0,1)的随机数，形式和x相同

x, y = Variable(x), Variable(y)

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
        # 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)
)
"""
'''
# 可视化
plt.plot()
plt.show()
'''

# 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)

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

    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

    """   
    # 接着上面来
    if t % 5 == 0:
        # plot and show learning process
        plt.cla()
        plt.scatter(x.data.numpy(), y.data.numpy())  # 打印散点图
        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()
    """

# 分类
import torch
import torch.nn.functional as F     # 激励函数都在这
import matplotlib.pyplot as plt
from torch.autograd import Variable

# data
n_data = torch.ones(100, 2)      # 基数
x0 = torch.normal(2*n_data, 1)   # class0 data (tensor), shape=(100, 2)
y0 = torch.zeros(100)            # class0 lable (tensor), shape=(100, 1)
x1 = torch.normal(-2*n_data, 1)  # class1 data (tensor), shape=(100, 2)
y1 = torch.ones(100)             # class1 lable (tensor), shape=(100, 1) 

# 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)  # 两类数据合并 FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)    # 两类标签合并 LongTensor = 64-bit integer

x, y = Variable(x), Variable(y)  # 放入篮子

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
        # 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
        x = F.relu(self.hidden(x))      
        x = self.predict(x)             
        return x

net = Net(n_feature=2, n_hidden=10, n_output=2)

"""
print(net)  # net 的结构
Net (
  (hidden): Linear (2 -> 10)
  (predict): Linear (10 -> 2)
)
"""

# optimizer 是训练的工具
optimizer = torch.optim.SGD(net.parameters(), lr=0.03)  # 传入 net 的所有参数, 学习率
loss_func = torch.nn.CrossEntropyLoss()      # 预测值和真实值的误差计算公式

for t in range(50):
    out = net(x)            # 喂给 net 训练数据 x, 输出预测值

    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

    # 接着上面来
    if t % 2 == 0:
        plt.cla()
        prediction = torch.max(F.softmax(out), 1)[1]
        pred_y = prediction.data.numpy().squeeze()
        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 = sum(pred_y == target_y)/200.  # 预测中有多少和真实值一样
        plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={
     'size': 20, 'color':  'red'})
        plt.pause(0.1)
        
    plt.ioff()  # 停止画图
    plt.show()

C:\Users\lenovo\Anaconda3\envs\pytorch\lib\site-packages\ipykernel_launcher.py:62: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.

### 快速搭建法
# 分类
import torch
import torch.nn.functional as F     # 激励函数都在这
import matplotlib.pyplot as plt
from torch.autograd import Variable

# data
n_data = torch.ones(100, 2)      # 基数
x0 = torch.normal(2*n_data, 1)   # class0 data (tensor), shape=(100, 2)
y0 = torch.zeros(100)            # class0 lable (tensor), shape=(100, 1)
x1 = torch.normal(-2*n_data, 1)  # class1 data (tensor), shape=(100, 2)
y1 = torch.ones(100)             # class1 lable (tensor), shape=(100, 1) 

# 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)  # 两类数据合并 FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)    # 两类标签合并 LongTensor = 64-bit integer

x, y = Variable(x), Variable(y)  # 放入篮子

# method 1
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
        # 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
        x = F.relu(self.hidden(x))      
        x = self.predict(x)             
        return x

net1 = Net(2, 10, 2)

# method 2
net2 = torch.nn.Sequential(
    torch.nn.Linear(2, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 2)
)

print(net1)
print(net2)

Net(
  (hidden): Linear(in_features=2, out_features=10, bias=True)
  (predict): Linear(in_features=10, out_features=2, bias=True)
)
Sequential(
  (0): Linear(in_features=2, out_features=10, bias=True)
  (1): ReLU()
  (2): Linear(in_features=10, out_features=2, bias=True)
)

# 保存和提取神经网络

# fake data
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))  # 创建一个画板
    plt.subplot(131)  # 第一个画板的第一个子图
    plt.title('Net1')
    plt.scatter(x.data.numpy(), y.data.numpy())                    # 散点
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=3)  # 描线

    # 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')  # 保存parameters (速度快, 占内存少)

# 还原网络
def restore_net():
    # restore entire net1 to net2
    net2 = torch.load('net.pkl')
    prediction = net2(x)  # 用于画图时的y轴坐标

    # plot result
    plt.subplot(132)  # 第一个画板的第二个子图
    plt.title('Net2')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=3)
    
# 还原参数  
def restore_params():
    # 新建 net3
    net3 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10,1)
    )
    # 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)  # 第一个画板的第三个子图
    plt.title('Net3')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=3)
    plt.show()
 
# 保存
save()

# 提取整个网络
restore_net()

# 提取网络参数, 复制到新网络
restore_params()