该博客主要通过阅读《HybridSN: Exploring 3-D–2-DCNN Feature Hierarchy for Hyperspectral Image Classification》,对论文中提出的HybridSN混合网络实现高光谱图像分类,本人通过Google Colab平台进行了实践。
作者提出HybridSN混合网络用于高光谱图像分类的研究。高光谱图像分析的研究由于其在现实生活中的潜在应用而具有重要意义。 高光谱成像导致多波段图像,使分析具有挑战性,因为数据量增加。 光谱,以及不同波段之间的空间相关性,传达了有关感兴趣场景的有用信息。
一、介绍
HSIs are volumetric data and have a spectral dimension as well. 仅使用2-D-CNN会导致缺失信道之间联系的信息,无法从光谱维度提取出良好的识别特征映射,仅使用3-D-CNN模型非常复杂,对于在许多谱带上具有相似纹理的类,性能更差,同时实验准确率也不高。论文提出了hybrid spectral CNN(HybridSN),HybridSN可以很好的解决这些问题.二、HybridSN
1.HybridSN网络
三维卷积部分:
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)
接下来要进行二维卷积,因此把前面的 32*18 reshape 一下,得到 (576, 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。
2.代码演示
首先取得数据,并引入基本函数库
! 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
构建HybridSN类
class_num = 16
class HybridSN(nn.Module):
def __init__(self):
super(HybridSN, self).__init__()
#三维卷积
self.conv3d_1 = nn.Sequential(
nn.Conv3d(1, 8, kernel_size=(7, 3, 3), stride=1, padding=0),
nn.BatchNorm3d(8),
nn.ReLU(inplace = True),
)
self.conv3d_2 = nn.Sequential(
nn.Conv3d(8, 16, kernel_size=(5, 3, 3), stride=1, padding=0),
nn.BatchNorm3d(16),
nn.ReLU(inplace = True),
)
self.conv3d_3 = nn.Sequential(
nn.Conv3d(16, 32, kernel_size=(3, 3, 3), stride=1, padding=0),
nn.BatchNorm3d(32),
nn.ReLU(inplace = True)
)
#二维卷积
self.conv2d_4 = nn.Sequential(
nn.Conv2d(576, 64, kernel_size=(3, 3), stride=1, padding=0),
nn.BatchNorm2d(64),
nn.ReLU(inplace = True),
)
self.fc1 = nn.Linear(18496,256)
self.fc2 = nn.Linear(256,128)
self.fc3 = nn.Linear(128,16)
self.dropout = nn.Dropout(p = 0.4)
def forward(self,x):
out = self.conv3d_1(x)
out = self.conv3d_2(out)
out = self.conv3d_3(out)
out = self.conv2d_4(out.reshape(out.shape[0],-1,19,19))
out = out.reshape(out.shape[0],-1)
out = F.relu(self.dropout(self.fc1(out)))
out = F.relu(self.dropout(self.fc2(out)))
out = self.fc3(out)
return out
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)
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')
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)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)
运行结果:
准确率达到了98.55%
备用函数:
下面是用于计算各个类准确率,显示结果的备用函数,以供参考
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
检测结果写在文件里
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))
下面代码用于显示分类结果:
# 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))
几次测试的分类结果图:
三、网络修改
1. 测试结果存在不同
问题:源代码中没有对训练模式和测试模式进行区分,采用了Batch Normalization(对网络中间的每层进行归一化处理,保证每层所提取的特征分布不会被破坏,训练时是正对每个min-batch的,但是在测试中往往是针对单张图片,即不存在min-batch的概念。由于网络训练完毕后参数都是固定的,因此每个批次的均值和方差都是不变的,因此直接结算所有batch的均值和方差。所以所有Batch Normalization的训练和测试时的操作不同)和Dropout(可以明显减少过拟合现象),网络训练稳定性强,但是在测试的过程中网络部分节点的随机失活使得每次测试的结果都不相同。
解决办法:
在训练模型时会在前面加上:
model.train()
在测试模型时在前面使用:
model.eval()
2. 引入注意力机制
class_num = 16
# 通道注意力机制
class ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
super(ChannelAttention, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.fc1 = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
out = avg_out + max_out
return self.sigmoid(out)
# 空间注意力机制
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
x = torch.cat([avg_out, max_out], dim=1)
x = self.conv1(x)
return self.sigmoid(x)
class HybridSN(nn.Module):
def __init__(self):
super(HybridSN, self).__init__()
#三维卷积
self.conv3d_1 = nn.Sequential(
nn.Conv3d(1, 8, kernel_size=(7, 3, 3), stride=1, padding=0),
nn.BatchNorm3d(8),
nn.ReLU(inplace = True),
)
self.conv3d_2 = nn.Sequential(
nn.Conv3d(8, 16, kernel_size=(5, 3, 3), stride=1, padding=0),
nn.BatchNorm3d(16),
nn.ReLU(inplace = True),
)
self.conv3d_3 = nn.Sequential(
nn.Conv3d(16, 32, kernel_size=(3, 3, 3), stride=1, padding=0),
nn.BatchNorm3d(32),
nn.ReLU(inplace = True)
)
#二维卷积
self.conv2d_4 = nn.Sequential(
nn.Conv2d(576, 64, kernel_size=(3, 3), stride=1, padding=0),
nn.BatchNorm2d(64),
nn.ReLU(inplace = True),
)
self.fc1 = nn.Linear(18496,256)
self.fc2 = nn.Linear(256,128)
self.fc3 = nn.Linear(128,16)
self.dropout = nn.Dropout(p = 0.4)
def forward(self,x):
out = self.conv3d_1(x)
out = self.conv3d_2(out)
out = self.conv3d_3(out)
out = self.conv2d_4(out.reshape(out.shape[0],-1,19,19))
out = out.reshape(out.shape[0],-1)
out = F.relu(self.dropout(self.fc1(out)))
out = F.relu(self.dropout(self.fc2(out)))
out = self.fc3(out)
return out
论文中提到可以从图像空间,通道,和光谱的波长三个方向使用注意力机制来处理特征,理论上是可以得到更好的效果的。
从实验看出准确率确实是提升了,但是不是很明显。