高光谱分类
-
高光谱遥感能够通过成像光谱仪在可见光、近红外、短波红外、中红外等电磁波谱范围获取近似连续的光谱曲线,将表征地物几何位置关系的空间信息与表征地物属性特征的光谱信息有机地融合在了一起,使得提取地物的细节信息成为可能。
-
再model中引入注意力机制
Hybrid-Spectral-Net for Hyperspectral Image Classification.
- HybridSN是频谱空间3D-CNN,然后是空间2D-CNN。 3D-CNN有助于从一堆光谱带中进行联合空间光谱特征表示。 在3D-CNN之上的2D-CNN进一步学习了更多抽象级别的空间表示。
- Model
colab 代码
https://colab.research.google.com/drive/1aZIZ284KfJUAhUNo1-hSuKW-Eo1QN5Te
#库文件
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
Model(已加入注意力机制)
#model
class_num = 16
class HybridSN(nn.Module):
def __init__(self):
super(HybridSN,self).__init__()
self.conv3d1 = nn.Conv3d(1,8,kernel_size=(7,3,3),stride=1,padding=0)
self.bn1 = nn.BatchNorm3d(8)
self.conv3d2 = nn.Conv3d(8,16,kernel_size=(5,3,3),stride=1,padding=0)
self.bn2 = nn.BatchNorm3d(16)
self.conv3d3 = nn.Conv3d(16,32,kernel_size=(3,3,3),stride=1,padding=0)
self.bn3 = nn.BatchNorm3d(32)
self.conv2d4 = nn.Conv2d(576,64,kernel_size=(3,3),stride=1,padding=0)
self.conv_atetetion=nn.Conv2d(576, 576, kernel_size=(1,1), stride=1, padding=0)
self.bn4 = nn.BatchNorm2d(64)
self.softmax=nn.Softmax(dim=1)
self.fc1 = nn.Linear(18496,8496)
self.fc2 = nn.Linear(8496,1024)
self.fc3 = nn.Linear(1024,1024)
self.fc4 = nn.Linear(1024,256)
self.fc5 = nn.Linear(256,128)
self.fc6 = nn.Linear(128,16)
self.dropout = nn.Dropout(0.4)
def attention(self, x):
b, c, h, w = x.size()
x_phi = self.conv_atetetion(x).view(b, c, -1)
x_theta = self.conv_atetetion(x).view(b, c, -1).permute(0, 2, 1).contiguous()
x_g = self.conv_atetetion(x).view(b, c, -1).permute(0, 2, 1).contiguous()
mul_theta_phi = torch.matmul(x_theta, x_phi)
mul_theta_phi = self.softmax(mul_theta_phi)
mul_theta_phi_g = torch.matmul(mul_theta_phi, x_g)
mul_theta_phi_g = mul_theta_phi_g.permute(0,2,1).contiguous().view(b, c, h, w)
mask = self.conv_atetetion(mul_theta_phi_g)
out = mask + x
return out
def forward(self,x):
out = F.relu(self.bn1(self.conv3d1(x)))
out = F.relu(self.bn2(self.conv3d2(out)))
out = F.relu(self.bn3(self.conv3d3(out)))
out = self.attention(out.reshape(out.shape[0],-1,19,19))
out = F.relu(self.bn4(self.conv2d4(out)))
out = out.reshape(out.shape[0],-1)
out = F.relu(self.dropout(self.fc1(out)))
out = F.relu(self.dropout(self.fc2(out)))
out = F.relu(self.dropout(self.fc3(out)))
out = F.relu(self.dropout(self.fc4(out)))
out = F.relu(self.dropout(self.fc5(out)))
out = self.fc6(out)
return out
#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)
# 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
# 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)
# 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')
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)
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))