前言
本片文章主要讨论基于HybridSN的高光谱图像分类(HSI),前序是阅读了一篇关于HybridSN的相关论文《HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification》,该论文中详细的介绍了HybirdSN的基础架构,其主要特点是采用了3-D-CNN与2-D-CNN相结合的方式,对比只采用3-D-CNN的高光谱分类方法,降低了模型复杂度,同时又弥补了2-D-CNN无法提取光谱维度特征的缺点。
Hybrid的架构如下:
各层表示如下:
代码实现
1、取得数据,引入基本函数库
! wget http://www.ehu.eus/ccwintco/uploads/6/67/Indian_pines_corrected.mat
! wget http://www.ehu.eus/ccwintco/uploads/c/c4/Indian_pines_gt.mat
! pip install spectral
import numpy as np
import matplotlib.pyplot as plt
import scipy.io as sio
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, accuracy_score, classification_report, cohen_kappa_score
import spectral
import torch
import torchvision
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
2、定义HybridSN类
可以从架构图中看到其三维卷积:
conv1:(1, 30, 25, 25), 8个 7x3x3 的卷积核 ==>(8, 24, 23, 23)
conv2:(8, 24, 23, 23), 16个 5x3x3 的卷积核 ==>(16, 20, 21, 21)
conv3:(16, 20, 21, 21),32个 3x3x3 的卷积核 ==>(32, 18, 19, 19)
二维卷积:(576, 19, 19) 64个 3x3 的卷积核,得到 (64, 17, 17)
接下来是一个 flatten 操作,变为 18496 维的向量,
接下来依次为256,128节点的全连接层,都使用比例为0.4的 Dropout,
最后输出为 16 个节点,是最终的分类类别数。
class HybridSN(nn.Module):
#继承父类初始化
def __init__(self):
super().__init__()
#三维卷积
self.conv3d_1 = nn.Sequential(
nn.Conv3d(1, 8, kernel_size=(7, 3, 3), stride=1, padding=0),
nn.ReLU(),
)
self.conv3d_2 = nn.Sequential(
nn.Conv3d(8, 16, kernel_size=(5, 3, 3), stride=1, padding=0),
nn.ReLU(),
)
self.conv3d_3 = nn.Sequential(
nn.Conv3d(16, 32, kernel_size=(3, 3, 3), stride=1, padding=0),
nn.ReLU()
)
#二维卷积
self.conv2d = nn.Sequential(
nn.Conv2d(576, 64, kernel_size=(3, 3), stride=1, padding=0),
nn.ReLU(),
)
#flatten
self.dense_layer1 = nn.Sequential(nn.Linear(18496,256),nn.ReLU(),nn.Dropout(0.4))
self.dense_layer2 = nn.Sequential(nn.Linear(256,128),nn.ReLU(),nn.Dropout(0.4))
self.output_layer = nn.Sequential(nn.Linear(128,16),nn.LogSoftmax(dim=1))
def forward(self,x):
#三维卷积
out = self.conv3d_1(x)
out = self.conv3d_2(out)
out = self.conv3d_3(out)
#二维卷积
out = out.view(-1, out.shape[1] * out.shape[2], out.shape[3], out.shape[4])
out = self.conv2d(out)
out = out.view(x.size(0), -1)
out = self.dense_layer1(out)
out = self.dense_layer2(out)
out = self.output_layer(out)
return out
测试代码:
# 随机输入,测试网络结构是否通
x = torch.randn(1, 1, 30, 25, 25)
net = HybridSN()
y = net(x)
print(y.shape)
输出为如下:
3、创建数据集
首先对高光谱数据实施PCA降维;然后创建 keras 方便处理的数据格式;然后随机抽取 10% 数据做为训练集,剩余的做为测试集。
首先定义基本函数:
# 对高光谱数据 X 应用 PCA 变换
def applyPCA(X, numComponents):
newX = np.reshape(X, (-1, X.shape[2]))
pca = PCA(n_components=numComponents, whiten=True)
newX = pca.fit_transform(newX)
newX = np.reshape(newX, (X.shape[0], X.shape[1], numComponents))
return newX
# 对单个像素周围提取 patch 时,边缘像素就无法取了,因此,给这部分像素进行 padding 操作
def padWithZeros(X, margin=2):
newX = np.zeros((X.shape[0] + 2 * margin, X.shape[1] + 2* margin, X.shape[2]))
x_offset = margin
y_offset = margin
newX[x_offset:X.shape[0] + x_offset, y_offset:X.shape[1] + y_offset, :] = X
return newX
# 在每个像素周围提取 patch ,然后创建成符合 keras 处理的格式
def createImageCubes(X, y, windowSize=5, removeZeroLabels = True):
# 给 X 做 padding
margin = int((windowSize - 1) / 2)
zeroPaddedX = padWithZeros(X, margin=margin)
# split patches
patchesData = np.zeros((X.shape[0] * X.shape[1], windowSize, windowSize, X.shape[2]))
patchesLabels = np.zeros((X.shape[0] * X.shape[1]))
patchIndex = 0
for r in range(margin, zeroPaddedX.shape[0] - margin):
for c in range(margin, zeroPaddedX.shape[1] - margin):
patch = zeroPaddedX[r - margin:r + margin + 1, c - margin:c + margin + 1]
patchesData[patchIndex, :, :, :] = patch
patchesLabels[patchIndex] = y[r-margin, c-margin]
patchIndex = patchIndex + 1
if removeZeroLabels:
patchesData = patchesData[patchesLabels>0,:,:,:]
patchesLabels = patchesLabels[patchesLabels>0]
patchesLabels -= 1
return patchesData, patchesLabels
def splitTrainTestSet(X, y, testRatio, randomState=345):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=testRatio, random_state=randomState, stratify=y)
return X_train, X_test, y_train, y_test
读取并创建数据集:
# 地物类别
class_num = 16
X = sio.loadmat('Indian_pines_corrected.mat')['indian_pines_corrected']
y = sio.loadmat('Indian_pines_gt.mat')['indian_pines_gt']
# 用于测试样本的比例
test_ratio = 0.90
# 每个像素周围提取 patch 的尺寸
patch_size = 25
# 使用 PCA 降维,得到主成分的数量
pca_components = 30
print('Hyperspectral data shape: ', X.shape)
print('Label shape: ', y.shape)
print('\n... ... PCA tranformation ... ...')
X_pca = applyPCA(X, numComponents=pca_components)
print('Data shape after PCA: ', X_pca.shape)
print('\n... ... create data cubes ... ...')
X_pca, y = createImageCubes(X_pca, y, windowSize=patch_size)
print('Data cube X shape: ', X_pca.shape)
print('Data cube y shape: ', y.shape)
print('\n... ... create train & test data ... ...')
Xtrain, Xtest, ytrain, ytest = splitTrainTestSet(X_pca, y, test_ratio)
print('Xtrain shape: ', Xtrain.shape)
print('Xtest shape: ', Xtest.shape)
# 改变 Xtrain, Ytrain 的形状,以符合 keras 的要求
Xtrain = Xtrain.reshape(-1, patch_size, patch_size, pca_components, 1)
Xtest = Xtest.reshape(-1, patch_size, patch_size, pca_components, 1)
print('before transpose: Xtrain shape: ', Xtrain.shape)
print('before transpose: Xtest shape: ', Xtest.shape)
# 为了适应 pytorch 结构,数据要做 transpose
Xtrain = Xtrain.transpose(0, 4, 3, 1, 2)
Xtest = Xtest.transpose(0, 4, 3, 1, 2)
print('after transpose: Xtrain shape: ', Xtrain.shape)
print('after transpose: Xtest shape: ', Xtest.shape)
""" Training dataset"""
class TrainDS(torch.utils.data.Dataset):
def __init__(self):
self.len = Xtrain.shape[0]
self.x_data = torch.FloatTensor(Xtrain)
self.y_data = torch.LongTensor(ytrain)
def __getitem__(self, index):
# 根据索引返回数据和对应的标签
return self.x_data[index], self.y_data[index]
def __len__(self):
# 返回文件数据的数目
return self.len
""" Testing dataset"""
class TestDS(torch.utils.data.Dataset):
def __init__(self):
self.len = Xtest.shape[0]
self.x_data = torch.FloatTensor(Xtest)
self.y_data = torch.LongTensor(ytest)
def __getitem__(self, index):
# 根据索引返回数据和对应的标签
return self.x_data[index], self.y_data[index]
def __len__(self):
# 返回文件数据的数目
return self.len
# 创建 trainloader 和 testloader
trainset = TrainDS()
testset = TestDS()
train_loader = torch.utils.data.DataLoader(dataset=trainset, batch_size=128, shuffle=True, num_workers=2)
test_loader = torch.utils.data.DataLoader(dataset=testset, batch_size=128, shuffle=False, num_workers=2)
4、开始训练
# 使用GPU训练,可以在菜单 "代码执行工具" -> "更改运行时类型" 里进行设置
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# 网络放到GPU上
net = HybridSN().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
# 开始训练
total_loss = 0
for epoch in range(100):
for i, (inputs, labels) in enumerate(train_loader):
inputs = inputs.to(device)
labels = labels.to(device)
# 优化器梯度归零
optimizer.zero_grad()
# 正向传播 + 反向传播 + 优化
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
total_loss += loss.item()
print('[Epoch: %d] [loss avg: %.4f] [current loss: %.4f]' %(epoch + 1, total_loss/(epoch+1), loss.item()))
print('Finished Training')
训练结果:
5、模型测试
count = 0
# 模型测试
for inputs, _ in test_loader:
inputs = inputs.to(device)
outputs = net(inputs)
outputs = np.argmax(outputs.detach().cpu().numpy(), axis=1)
if count == 0:
y_pred_test = outputs
count = 1
else:
y_pred_test = np.concatenate( (y_pred_test, outputs) )
# 生成分类报告
classification = classification_report(ytest, y_pred_test, digits=4)
print(classification)
测试结果:正确率96.64%
6、显示分类结果代码及最终结果:
from operator import truediv
def AA_andEachClassAccuracy(confusion_matrix):
counter = confusion_matrix.shape[0]
list_diag = np.diag(confusion_matrix)
list_raw_sum = np.sum(confusion_matrix, axis=1)
each_acc = np.nan_to_num(truediv(list_diag, list_raw_sum))
average_acc = np.mean(each_acc)
return each_acc, average_acc
def reports (test_loader, y_test, name):
count = 0
# 模型测试
for inputs, _ in test_loader:
inputs = inputs.to(device)
outputs = net(inputs)
outputs = np.argmax(outputs.detach().cpu().numpy(), axis=1)
if count == 0:
y_pred = outputs
count = 1
else:
y_pred = np.concatenate( (y_pred, outputs) )
if name == 'IP':
target_names = ['Alfalfa', 'Corn-notill', 'Corn-mintill', 'Corn'
,'Grass-pasture', 'Grass-trees', 'Grass-pasture-mowed',
'Hay-windrowed', 'Oats', 'Soybean-notill', 'Soybean-mintill',
'Soybean-clean', 'Wheat', 'Woods', 'Buildings-Grass-Trees-Drives',
'Stone-Steel-Towers']
elif name == 'SA':
target_names = ['Brocoli_green_weeds_1','Brocoli_green_weeds_2','Fallow','Fallow_rough_plow','Fallow_smooth',
'Stubble','Celery','Grapes_untrained','Soil_vinyard_develop','Corn_senesced_green_weeds',
'Lettuce_romaine_4wk','Lettuce_romaine_5wk','Lettuce_romaine_6wk','Lettuce_romaine_7wk',
'Vinyard_untrained','Vinyard_vertical_trellis']
elif name == 'PU':
target_names = ['Asphalt','Meadows','Gravel','Trees', 'Painted metal sheets','Bare Soil','Bitumen',
'Self-Blocking Bricks','Shadows']
classification = classification_report(y_test, y_pred, target_names=target_names)
oa = accuracy_score(y_test, y_pred)
confusion = confusion_matrix(y_test, y_pred)
each_acc, aa = AA_andEachClassAccuracy(confusion)
kappa = cohen_kappa_score(y_test, y_pred)
return classification, confusion, oa*100, each_acc*100, aa*100, kappa*100
classification, confusion, oa, each_acc, aa, kappa = reports(test_loader, ytest, 'IP')
classification = str(classification)
confusion = str(confusion)
file_name = "classification_report.txt"
with open(file_name, 'w') as x_file:
x_file.write('\n')
x_file.write('{} Kappa accuracy (%)'.format(kappa))
x_file.write('\n')
x_file.write('{} Overall accuracy (%)'.format(oa))
x_file.write('\n')
x_file.write('{} Average accuracy (%)'.format(aa))
x_file.write('\n')
x_file.write('\n')
x_file.write('{}'.format(classification))
x_file.write('\n')
x_file.write('{}'.format(confusion))
# load the original image
X = sio.loadmat('Indian_pines_corrected.mat')['indian_pines_corrected']
y = sio.loadmat('Indian_pines_gt.mat')['indian_pines_gt']
height = y.shape[0]
width = y.shape[1]
X = applyPCA(X, numComponents= pca_components)
X = padWithZeros(X, patch_size//2)
# 逐像素预测类别
outputs = np.zeros((height,width))
for i in range(height):
for j in range(width):
if int(y[i,j]) == 0:
continue
else :
image_patch = X[i:i+patch_size, j:j+patch_size, :]
image_patch = image_patch.reshape(1,image_patch.shape[0],image_patch.shape[1], image_patch.shape[2], 1)
X_test_image = torch.FloatTensor(image_patch.transpose(0, 4, 3, 1, 2)).to(device)
prediction = net(X_test_image)
prediction = np.argmax(prediction.detach().cpu().numpy(), axis=1)
outputs[i][j] = prediction+1
if i % 20 == 0:
print('... ... row ', i, ' handling ... ...')
predict_image = spectral.imshow(classes = outputs.astype(int),figsize =(5,5))
7、考虑加入注意力机制,由于了解的注意力机制代码不是很多,所以直接使用了在ImageNe2017中获得冠军的SENet中的SE模块,这个模块思想简单,且容易加载到现在的网络模型框架中。代码段如下:
class SELayer(nn.Module):
def __init__(self, channel, reduction=16):
super(SELayer, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Sequential(
nn.Linear(channel, channel // reduction, bias=False),
nn.ReLU(inplace=True),
nn.Linear(channel // reduction, channel, bias=False),
nn.Sigmoid()
)
def forward(self, x):
b, c, _, _ = x.size()
y = self.avg_pool(x).view(b, c)
y = self.fc(y).view(b, c, 1, 1)
return x * y.expand_as(x)
加入SElayer之后的HybridSN代码如下:
class HybridSN(nn.Module):
#继承父类初始化
def __init__(self):
super().__init__()
#三维卷积
self.conv3d_1 = nn.Sequential(
nn.Conv3d(1, 8, kernel_size=(7, 3, 3), stride=1, padding=0),
nn.ReLU(),
)
self.conv3d_2 = nn.Sequential(
nn.Conv3d(8, 16, kernel_size=(5, 3, 3), stride=1, padding=0),
nn.ReLU(),
)
self.conv3d_3 = nn.Sequential(
nn.Conv3d(16, 32, kernel_size=(3, 3, 3), stride=1, padding=0),
nn.ReLU()
)
self.selayer = SElayer(64,16)
#二维卷积
self.conv2d = nn.Sequential(
nn.Conv2d(576, 64, kernel_size=(3, 3), stride=1, padding=0),
nn.ReLU(),
)
#flatten
self.dense_layer1 = nn.Sequential(nn.Linear(18496,256),nn.ReLU(),nn.Dropout(0.4))
self.dense_layer2 = nn.Sequential(nn.Linear(256,128),nn.ReLU(),nn.Dropout(0.4))
self.output_layer = nn.Sequential(nn.Linear(128,16),nn.LogSoftmax(dim=1))
def forward(self,x):
#三维卷积
out = self.conv3d_1(x)
out = self.conv3d_2(out)
out = self.conv3d_3(out)
#二维卷积
out = out.view(-1, out.shape[1] * out.shape[2], out.shape[3], out.shape[4])
out = self.conv2d(out)
out = self.selayer(out)
out = out.view(x.size(0), -1)
out = self.dense_layer1(out)
out = self.dense_layer2(out)
out = self.output_layer(out)
return out
8、重新训练
9、重新测试
准确率提高了,进行分类结果查看
最终分类结果:
可以看到准确率有所提升,分类结果也变得更好了。
问题:
1、3D卷积和2D卷积的区别
2D卷积只能提取二维特征,只能提取空间特征而不能提取光谱特征;
3D卷积多一个维度可以提取更多的特征,但是计算会更复杂。
2、训练网络,然后多测试几次,会发现每次分类的结果都不一样,请思考为什么?
初始阈值不同,初始权值随机
dropout时同样带有随机性