基本概念
概述
卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Network,CNN)是一種深度學(xué)習(xí)中常用于處理具有網(wǎng)格結(jié)構(gòu)數(shù)據(jù)的神經(jīng)網(wǎng)絡(luò)模型。它在計算機視覺領(lǐng)域廣泛應(yīng)用于圖像分類、目標(biāo)檢測、圖像生成等任務(wù)。
核心思想
CNN 的核心思想是通過利用局部感知和參數(shù)共享來捕捉輸入數(shù)據(jù)的空間結(jié)構(gòu)信息。相比于傳統(tǒng)的全連接神經(jīng)網(wǎng)絡(luò),CNN 在網(wǎng)絡(luò)結(jié)構(gòu)中引入了卷積層和池化層,從而減少了參數(shù)量,并且能夠更好地處理高維輸入數(shù)據(jù)。
其他概念
輸入層:接收原始圖像或其他形式的輸入數(shù)據(jù)。
卷積層(Convolutional Layer):使用卷積操作提取輸入特征,通過設(shè)置濾波器(卷積核)在輸入數(shù)據(jù)上滑動并執(zhí)行卷積運算。這樣可以學(xué)習(xí)到局部的特征,如邊緣、紋理等。
激活函數(shù)(Activation Function):在每個卷積層后面通常緊跟一個非線性的激活函數(shù),如ReLU(Rectified Linear Unit),以增加網(wǎng)絡(luò)的非線性表達能力。
池化層(Pooling Layer):通過減少特征圖的尺寸來降低模型復(fù)雜性。常用的池化操作是最大池化(Max Pooling),它選取每個池化窗口內(nèi)的最大特征值作為輸出。
全連接層(Fully Connected Layer):將卷積層和池化層的輸出連接到全連接層,使用傳統(tǒng)的神經(jīng)網(wǎng)絡(luò)模式進行分類、回歸等任務(wù)。
Dropout 層:在訓(xùn)練過程中以一定概率隨機將部分神經(jīng)元的輸出置為0,以減少模型的過擬合。
Softmax 層:多分類問題中常用的輸出層,在最后一層進行 softmax 操作將輸出轉(zhuǎn)化為類別上的概率分布。
代碼與詳細(xì)注釋
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
# 輪次
EPOCH = 1 # train the training data n times, to save time, we just train 1 epoch
# 批大小為50
BATCH_SIZE = 50
# 學(xué)習(xí)率
LR = 0.001
# 是否下載mnist數(shù)據(jù)集
DOWNLOAD_MNIST = False
# 下載minist數(shù)據(jù)集
if not(os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
# not mnist dir or mnist is empyt dir
DOWNLOAD_MNIST = True
# torchvision本身就是一個數(shù)據(jù)庫
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,
)
# 輸出訓(xùn)練數(shù)據(jù)尺寸
print(train_data.train_data.size()) # (60000, 28, 28)
# 輸出標(biāo)簽數(shù)據(jù)尺寸
print(train_data.train_labels.size()) # (60000)
# 展示訓(xùn)練數(shù)據(jù)集中的第0個圖片
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
# 圖片的標(biāo)題是標(biāo)簽
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)
# 批大小為50,shuffle為True意思是設(shè)置為隨機
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)
# 使用unsqueeze增加一個維度
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__()
# 快速搭建神經(jīng)網(wǎng)絡(luò)
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
# 前向傳播
def forward(self, x):
# 第一層卷積
x = self.conv1(x)
# 第二層卷積
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
# 選擇優(yōu)化器
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR) # optimize all cnn parameters
# 選擇損失函數(shù)
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')
運行結(jié)果
文章來源:http://www.zghlxwxcb.cn/news/detail-555933.html
文章來源地址http://www.zghlxwxcb.cn/news/detail-555933.html
到了這里,關(guān)于深度學(xué)習(xí)——CNN卷積神經(jīng)網(wǎng)絡(luò)的文章就介紹完了。如果您還想了解更多內(nèi)容,請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章,希望大家以后多多支持TOY模板網(wǎng)!