神经网络的快速搭建
快速搭建法
逐层加上激励函数直接构造
# method 2
# 快速搭建
net2 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1),
)
print(net2)
out
Sequential(
(0): Linear(in_features=1, out_features=10, bias=True)
(1): ReLU()
(2): Linear(in_features=10, out_features=1, bias=True)
)
批训练
import torch
import torch.utils.data as Data
BATCH_SIZE = 5
x = torch.linspace(1, 10, 10)
y = torch.linspace(10, 1, 10)
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(
dataset=torch_dataset, # 数据集
batch_size=BATCH_SIZE,
shuffle=True, # 训练时需不需要打乱
# num_workers = 2 # 此破电脑不能多线程
)
for epoch in range(3): # 整体训练三次
for step, (batch_x, batch_y) in enumerate(loader):
# training
print('Epoch', epoch, '|Step:', step, '|batch x:',
batch_x.numpy(), '|batch y:', batch_y.numpy())
out
Epoch 0 |Step: 0 |batch x: [9. 2. 7. 4. 3.] |batch y: [2. 9. 4. 7. 8.]
Epoch 0 |Step: 1 |batch x: [ 8. 1. 5. 6. 10.] |batch y: [ 3. 10. 6. 5. 1.]
Epoch 1 |Step: 0 |batch x: [ 3. 7. 6. 10. 8.] |batch y: [8. 4. 5. 1. 3.]
Epoch 1 |Step: 1 |batch x: [9. 1. 2. 4. 5.] |batch y: [ 2. 10. 9. 7. 6.]
Epoch 2 |Step: 0 |batch x: [10. 5. 4. 8. 7.] |batch y: [1. 6. 7. 3. 4.]
Epoch 2 |Step: 1 |batch x: [1. 9. 3. 6. 2.] |batch y: [10. 2. 8. 5. 9.]
可以用data_loader进行批训练
加速神经网络训练过程
SGD
stochastic Gradient Descent
批量数据进入神经网络训练
Mumentum: m = b 1 ∗ m − l e a r n i n g r a t e ∗ d x m=b_1*m-learning\ rate*dx m=b1∗m−learning rate∗dx
adagrad: v + = d x 2 v+=dx^2 v+=dx2
结合之后得出RMSProp
m = b 1 ∗ m + ( 1 − b 1 ) ∗ d x m=b_1*m+(1-b_1)*dx m=b1∗m+(1−b1)∗dx Momentum:下坡
v = b 2 ∗ v + ( 1 − b 2 ) ∗ d x 2 v=b_2*v+(1-b_2)*dx^2 v=b2∗v+(1−b2)∗dx2 AdaGrad:阻力太大,只能沿着下降方向
w + = − l e a r i n g r a t e ∗ m / v w += -learing \ rate * m / \sqrt{v} w+=−learing rate∗m/v
CNN卷积神经网络
处理图片识别:将图片变成一个个像素,并不是对一个个像素进行处理,而是对一块像素区域进行处理。
采用一个过滤器在图片中不断移动,这叫做卷积
然后输出一个长和宽更小,高度更大的图片
在卷积的过程中,可能会丢失一些信息,则需要进行池化
pytorch实现
我们采用MNIST数据集
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
EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = True
train_data = torchvision.datasets.MNIST(
root='./mnist',
train=True,
transform=torchvision.transforms.ToTensor(), # 改成tensor格式
download=DOWNLOAD_MNIST
)
# plot one example
print(train_data.train_data.size())
print(train_data.train_labels.size())
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()
输出有一张5
构建cnn卷积神经网络
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
EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False
train_data = torchvision.datasets.MNIST(
root='./mnist',
train=True,
transform=torchvision.transforms.ToTensor(), # 改成tensor格式
download=DOWNLOAD_MNIST
)
# plot one example
# print(train_data.train_data.size())
# print(train_data.train_labels.size())
# plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
# plt.title('%i' % train_data.train_labels[0])
# plt.show()
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
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
test_y = test_data.test_labels[:2000]
class CNN(nn.Module):
# 卷积层
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(
in_channels=1, # 图片的高度
out_channels=16, # 输出的高度(特征个数)
kernel_size=5, # filter宽和高都是5(5*5)的扫描形式
stride=1, # 隔几步跳一次
padding=2 # 周围围上一圈0, padding = (kernel_size - 1) / 2
), # 过滤器 -> (16, 28, 28)
nn.ReLU(), # 卷积层
nn.MaxPool2d(kernel_size=2), # 池化层,保留重要特征 ->(16, 14, 14)
)
self.conv2 = nn.Sequential( # (16, 14, 14)
nn.Conv2d(16,32,5,1,2), # ->(32, 14, 14)
nn.ReLU(),
nn.MaxPool2d(2) # -> (32, 7, 7)
)
self.out = nn.Linear(32 * 7 * 7, 10)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x) # (batch, 32, 7, 7)
x = x.view(x.size(0), -1) # (batch, 32 * 7 * 7)
cnn = CNN()
print(cnn)
out
CNN(
(conv1): Sequential(
(0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): ReLU()
(2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(conv2): Sequential(
(0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): ReLU()
(2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(out): Linear(in_features=1568, out_features=10, bias=True)
)
加上优化器与训练之后
"""
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
import matplotlib.pyplot as plt
# torch.manual_seed(1) # reproducible
# Hyper Parameters
EPOCH = 1 # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 50
LR = 0.001 # learning rate
DOWNLOAD_MNIST = 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
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,
)
# 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)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
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)
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, # if want same width and length of this image after Conv2d, padding=(kernel_size-1)/2 if stride=1
), # output shape (16, 28, 28)
nn.ReLU(), # activation
nn.MaxPool2d(kernel_size=2), # choose max value in 2x2 area, 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)
x = x.view(x.size(0), -1) # flatten the output of conv2 to (batch_size, 32 * 7 * 7)
output = self.out(x)
return output, x # return x for visualization
cnn = CNN()
print(cnn) # net architecture
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
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()
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')
out
[7 2 1 0 4 1 4 9 5 9] prediction number
[7 2 1 0 4 1 4 9 5 9] real number