目录
1.代码练习
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
定义 HybridSN 类
模型的网络结构为如下图所示: HybridSN
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。
下面是 HybridSN 类的代码:
class_num = 16
class HybridSN(nn.Module):
def __init__(self, num_classes=16):
super(HybridSN, self).__init__()
# conv1:(1, 30, 25, 25), 8个 7x3x3 的卷积核 ==>(8, 24, 23, 23)
self.conv1 = nn.Conv3d(1, 8, (7, 3, 3))
# conv2:(8, 24, 23, 23), 16个 5x3x3 的卷积核 ==>(16, 20, 21, 21)
self.conv2 = nn.Conv3d(8, 16, (5, 3, 3))
# conv3:(16, 20, 21, 21),32个 3x3x3 的卷积核 ==>(32, 18, 19, 19)
self.conv3 = nn.Conv3d(16, 32, (3, 3, 3))
# conv3_2d (576, 19, 19),64个 3x3 的卷积核 ==>((64, 17, 17)
self.conv3_2d = nn.Conv2d(576, 64, (3,3))
# 全连接层(256个节点)
self.dense1 = nn.Linear(18496,256)
# 全连接层(128个节点)
self.dense2 = nn.Linear(256,128)
# 最终输出层(16个节点)
self.out = nn.Linear(128, num_classes)
# Dropout(0.4)
self.drop = nn.Dropout(p=0.4)\
# 最后不使用softmax效果更好
# self.soft = nn.Softmax(dim=1)
# 激活函数ReLU
self.relu = nn.ReLU()
def forward(self, x):
out = self.relu(self.conv1(x))
out = self.relu(self.conv2(out))
out = self.relu(self.conv3(out))
# 进行二维卷积,因此把前面的 32*18 reshape 一下,得到 (576, 19, 19)
out = out.view(-1, out.shape[1] * out.shape[2], out.shape[3], out.shape[4])
out = self.relu(self.conv3_2d(out))
# flatten 操作,变为 18496 维的向量,
out = out.view(out.size(0), -1)
out = self.dense1(out)
out = self.drop(out)
out = self.dense2(out)
out = self.drop(out)
out = self.out(out)
# out = self.soft(out)
return out
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))
2.思考题
(1)训练HybridSN,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?
①随机初始化:深度学习模型的参数通常是随机初始化的。这意味着在每次训练开始时,模型的初始参数值都不同,因此模型的学习路径可能会有所不同。
②随机采样:在每个epoch中,训练数据被随机采样形成不同的小批量,这导致每个批次的数据也不同。这会使得模型在每个批次上更新梯度,进而影响模型的学习方向。
③优化算法:常用的优化算法(如SGD、Adam等)基于随机梯度估计来更新参数。由于随机梯度是根据随机采样的小批量数据计算的,因此每个批次的梯度估计都会有一定的差异。
④并行计算:在使用GPU进行训练时,不同的GPU核心可能在不同时间执行计算,导致计算的顺序不同,进而影响参数的更新。
(2)如果想要进一步提升高光谱图像的分类性能,可以如何改进?
①数据增强:在训练数据上应用数据增强技术,如随机旋转、缩放、平移、翻转等操作,以增加数据样本的多样性,提高模型的泛化能力。
②网络结构优化:尝试改变网络结构,增加或减少网络的层数,调整卷积核大小、通道数等超参数,以适应数据集的特点。
③调整学习率:尝试使用学习率调度器来动态调整学习率,例如学习率衰减、余弦退火等策略,以更好地引导模型的训练过程。
④正则化:在损失函数中引入正则化项,如L1正则化、L2正则化,以防止过拟合。
⑤批标准化:在网络中引入批标准化层,有助于加速收敛并提高模型的泛化性能。
⑥深度监督:在网络中添加额外的分类器,用于多个阶段的监督训练,有助于缓解梯度消失问题。
⑦集成学习:尝试使用集成学习方法,如投票、堆叠等,将多个模型的预测结果结合起来,提高分类性能。
⑧特征工程:针对具体任务,对高光谱数据进行特征工程,提取更有意义的特征。
⑨超参数搜索:使用网格搜索或随机搜索等方法,寻找最优的超参数组合。
⑩迁移学习:考虑使用预训练的模型,如在大规模高光谱图像数据上预训练,然后在目标数据集上进行微调。
(3)depth-wise conv 和 分组卷积有什么区别与联系?
①分组卷积将输入和卷积核按照通道进行分组,每个组都有自己的卷积核。而深度可分离卷积在通道级上分别处理输入数据,然后再进行线性组合。
②分组卷积是在输入通道和输出通道上都进行分组,而深度可分离卷积仅在输入通道上进行分离。
③深度可分离卷积通常比分组卷积更轻量级,因为它只需要一个1x1的卷积核来进行线性组合,而分组卷积需要更多的卷积核进行计算。
④深度可分离卷积在移动端和嵌入式设备上广泛使用,以实现高效的计算和较小的模型体积。分组卷积通常应用于桌面计算和服务器端,用于加速大规模训练。
(4)SENet 的注意力是不是可以加在空间位置上?
是的,SENet的注意力机制可以被应用在空间位置上,用于增强模型对输入数据在不同空间位置的重要性区域的关注程度。
(5)在 ShuffleNet 中,通道的 shuffle 如何用代码实现?
在ShuffleNet中,通道的shuffle操作是通过将通道分成不同的组,并在组内进行通道交换来实现的。
import torch
import torch.nn as nn
class ChannelShuffle(nn.Module):
def __init__(self, groups):
super(ChannelShuffle, self).__init__()
self.groups = groups
def forward(self, x):
batch_size, num_channels, height, width = x.size()
channels_per_group = num_channels // self.groups
# 将特征图按组进行切分
x = x.view(batch_size, self.groups, channels_per_group, height, width)
# 将通道维度和组维度交换
x = x.permute(0, 2, 1, 3, 4)
# 将分组后的特征图展开为原始形状
x = x.view(batch_size, num_channels, height, width)
return x
# 示例
input_data = torch.randn(1, 16, 32, 32) # 输入数据大小为:[batch_size, num_channels, height, width]
groups = 4 # 设置分组数
shuffle_layer = ChannelShuffle(groups)
output_data = shuffle_layer(input_data)