pytorch笔记

pytorch

#mnist手写识别      CNN

训练使用的数据集是MNIST识别手写文字0-9，文字标签的编码方式为one-hot编码。 
导入库 (os,torch,nn,Data) -
设置epoch、批大小、学习率等
使用torchvision.datasets下载数据集并制作批训练分发器,train_data有train_data和train_labels两个子属性，以前2000条数据作为测试集加速测试过程 - 
定义CNN类（两层卷积层再全连接到10个节点表示数字，每层卷积后用ReLU激活，使用kernel_size为2的池化操作。） 
初始化网络，定义优化器和损失函数 
训练

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt

#hyper parameters超参数
EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

# 下载MNIST
train_data = torchvision.datasets.MNIST(
    root='./mnist',         #保存在文件夹中
    train=True,         #false则是测试点test
    transform=torchvision.transforms.ToTensor(),     #tensor数据的值在0-1之间 ，彩的0-255压缩到黑白的0-1
    download=DOWNLOAD_MNIST
    )
# #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()                                           ctrl+/ duohangzhushi

train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=2)

test_data = torchvision.datasets.MNIST(root='./mnist/',train=False)
test_x = Variable(torch.unsqueeze(test_data.test_data,dim=1),volatile=True).type(torch.FloatTensor)[:2000]/255    #shape
test_y = test_data.test_labels[:2000]   #取前000个标签y

#构建网络
class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(                          #卷积层          (28,28,1)
                in_channels=1,               #图片的高度，黑白1层
                out_channels=16,          #输出的高度，过滤器的个数
                kernel_size=5,               #过滤器是5*5*16
                stride=1,                  #步长 1
                padding=2                  #填充 0   如果步长是1，则padding=(kernal_size-1)/2, 为了保证与前面图片大小相等
            ),                                                 # (28,28,16)
            nn.ReLU(),           #jihuohanshu
            nn.MaxPool2d(kernel_size=2),        #池化层    2*2  高度不变   (14,14,16)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16,32,5,1,2),               #加工成32层      (14,14,32)
            nn.ReLU(),
            nn.MaxPool2d(2),                                       #(7,7,32)
        )
        self.out = nn.Linear(32*7*7,10)        #将三维的数据展评成二维的数据

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)       #batch,327,7
        x = x.view(x.size(0),-1)      # batch,32*7*7
        output = self.out(x)          #输出10
        return output
cnn = CNN()
#print(cnn)

#训练网络
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):
        b_x = Variable(x)
        b_y = Variable(y)            # gives batch data, normalize x when iterate train_loader

        output = cnn(b_x)               # cnn 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 = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.squeeze()
            accuracy = sum(pred_y == test_y) / test_y.size(0)
            print('Epoch:',epoch,'| train loss: %.4f' % loss.item())

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

。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。


RNN  classifier.py
仍对手写字体数据进行分类，由于序列较长，使用LSTM。 -
 导入库(torch,nn,torchvision -
 设置超参数（每张图片输入n个step，n表示图片高度，每个step输入一行像素信息） - 
获取数据集并制作训练集分发器 -
 定义RNN类 -
 事例化RNN，并选择优化方法和损失函数 -
 循环训练



import numpy as np
import torch
import torch.nn as nn
from torch.autograd import Variable
import torchvision
import matplotlib.pyplot as plt

# Hyper Parameters
EPOCH = 1
BATCH_SIZE = 64
TIME_STEP = 28      # rnn time step / image height
INPUT_SIZE = 28      # rnn input size / image width
LR = 0.01          # learning rate
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(
    root='./mnist',         #保存在文件夹中
    train=True,         #false则是测试点test
    transform=torchvision.transforms.ToTensor(),     #tensor数据的值在0-1之间 ，彩的0-255压缩到黑白的0-1
    download=DOWNLOAD_MNIST
    )
train_loader = torch.utils.data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=2)

test_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=False,
    transform=torchvision.transforms.ToTensor
    )
test_x = Variable(test_data.test_data,volatile=True).type(torch.FloatTensor)[:2000]/255    #shape
test_y = test_data.test_labels[:2000]   #取前1000个标签y


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

        self.rnn = nn.LSTM(
            input_size=INPUT_SIZE,     #28
            hidden_size=64,     # rnn hidden unit
            num_layers=1,       # number of rnn layer   hidden layer=1
            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)

    def forward(self, x):
        # x (batch, time_step, input_size)
        # h_state (n_layers, batch, hidden_size)
        # r_out (batch, time_step, hidden_size)
        r_out, (h_n,h_c) = self.rnn(x, None)
        out = self.out(r_out[:,-1,:])# save all predictions
        return out
rnn = RNN()


optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()        #不是0，1 这种，标签是7他显示的就是7


for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):       #give batch data
        b_x = Variable(x.view(-1,28,28))              # reshape x to (batch, time_step, input_size)
        b_y = Variable(y)                     #view()函数可以将原来的向量先转成一维向量，然后再生成指定维数的向量。
        output = rnn(b_x)
        loss = loss_func(output, y)         # calculate 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)
            pred_y = torch.max(test_output, 1)[1].data.squeeze()
            accuracy = sum(pred_y == test_y) / test_y.size(0)
            print('Epoch:', epoch, '| train loss: %.4f' % loss.item(),'| 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().squeeze()
print(pred_y, 'prediction number')
print(test_y[:10], 'real number')

。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。

RNN_regressor.py

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(
            input_size=INPUT_SIZE,
            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, hidden_size)
        r_out, h_state = self.rnn(x, h_state)

        outs = []    # save all predictions
        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

        # 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)

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

h_state = None      # for initial 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()

。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。

自动编码器autoencoder
    导入模块设置超参数下载数据集，并制作训练集的批训练分发器（自编码器是一种广义的无监督学习，没有标签数据，先通过encoder网络压缩成低维数据，再拓展成高维数据，目标是扩展后能与原始数据一致。这样训练得到的中间产物——低维数据，可以认为提炼了原数据最重要的特征，可以输入其他网络执行下游任务。由于原始数据同时承担了x和y的作用，没有使用金标准的标签数据，可以认为是一种无监督学习。）定义自动编码器的函数初始化Autoencoder并选择优化方式和损失函数。循环训练

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
N_TEST_IMG = 5

# 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)


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),   # compress to 3 features which can be visualized in plt
        )
        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(),       # compress to a range (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()

。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。
GAN

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
    G_paintings = G(G_ideas)                    # fake painting from G (random ideas)
    prob_artist1 = D(G_paintings)               # D try to reduce this prob
    G_loss = torch.mean(torch.log(1. - prob_artist1))  
    opt_G.zero_grad()
    G_loss.backward()
    opt_G.step()
     
    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))
    opt_D.zero_grad()
    D_loss.backward(retain_graph=True)      # reusing computational graph
    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()

。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。
_why_torch_dynamic_graph.py

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
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')
。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。
503_dropout.py

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),
    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()
        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()

。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。

504_batch_normalization.py

import torch
from torch import nn
from torch.nn import init
import torch.utils.data as Data
import matplotlib.pyplot as plt
import numpy as np

# torch.manual_seed(1)    # reproducible
# np.random.seed(1)

# Hyper parameters
N_SAMPLES = 2000
BATCH_SIZE = 64
EPOCH = 12
LR = 0.03
N_HIDDEN = 8
ACTIVATION = torch.tanh
B_INIT = -0.2   # use a bad bias constant initializer

# training data
x = np.linspace(-7, 10, N_SAMPLES)[:, np.newaxis]
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)
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')


class Net(nn.Module):
    def __init__(self, batch_normalization=False):
        super(Net, self).__init__()
        self.do_bn = batch_normalization
        self.fcs = []
        self.bns = []
        self.bn_input = nn.BatchNorm1d(1, momentum=0.5)   # for input data

        for i in range(N_HIDDEN):               # build hidden layers and BN layers
            input_size = 1 if i == 0 else 10
            fc = nn.Linear(input_size, 10)
            setattr(self, 'fc%i' % i, fc)       # IMPORTANT set layer to the Module
            self._set_init(fc)                  # parameters initialization
            self.fcs.append(fc)
            if self.do_bn:
                bn = nn.BatchNorm1d(10, momentum=0.5)
                setattr(self, 'bn%i' % i, bn)   # IMPORTANT set layer to the Module
                self.bns.append(bn)

        self.predict = nn.Linear(10, 1)         # output layer
        self._set_init(self.predict)            # parameters initialization

    def _set_init(self, layer):
        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)     # input batch normalization
        layer_input = [x]
        for i in range(N_HIDDEN):
            x = self.fcs[i](x)
            pre_activation.append(x)
            if self.do_bn: x = self.bns[i](x)   # batch normalization
            x = ACTIVATION(x)
            layer_input.append(x)
        out = self.predict(x)
        return out, layer_input, pre_activation

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

    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        layer_inputs, pre_acts = [], []
        for net, l in zip(nets, losses):
            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

    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()