【遥感影像分类】使用PaddleAPI搭建ResNet50实现遥感影像分类任务

本文围绕遥感分类任务展开，使用西北工业大学2016年发布的含45类土地利用类型的遥感影像数据集，构建RESISC45Dataset自定义数据集，搭建ResNet50模型，经训练、验证，模型精度达0.83左右，最后进行了模型预测与效果展示。

☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 免费无限量使用 DeepSeek R1 模型☜☜☜

前言

①. 关于任务

遥感分类，是指根据不同的分类标志以及遥感探测及应用侧重的方面不同，将遥感分成不同的类型。遥感图像计算机分类的依据是遥感图像像素的相似度。常使用距离和相关系数来衡量相似度。常见的分类方法有：监督分类、非监督分类法。

按遥感平台的不同，可把遥感分为航天遥感、航空遥感和地面（近地）遥感。按探测的电磁波段不同，可分为可见光遥感，红外遥感，微波遥感等。

②. 关于数据集

该数据集是由西北工业大学于2016年发布，包含提取自Google Earth的45种土地利用类型的遥感影像

数据集包含45个类别文件夹，每个文件夹下对应各自700幅遥感影像，一共有31500幅。

影像文件为三通道、大小为256*256的jpg格式文件

数据准备

解压已预先划分好的数据集

In [2]

# 解压数据集!unzip -oq /home/aistudio/data/data131697/NWPU-RESISC45.zip

   In [3]

# 查看数据集文件结构!tree NWPU-RESISC45 -L 1

自定义数据集

In [1]

# 导入包import paddlefrom PIL import Imageimport osimport numpy as npimport random# 打印paddle版本print(paddle.__version__)

2.2.2

       In [3]

class RESISC45Dataset(paddle.io.Dataset):    def __init__(self, mode='train', label_path='NWPU-RESISC45/train_list.txt'):        """        初始化函数        """        assert mode in ['train', 'eval', 'test'], 'mode is one of train, eval, test.'        self.mode = mode.lower()        self.label_path = label_path        self.data = []        with open(label_path) as f:            for line in f.readlines():                info = line.strip().split(' ')                if len(info) > 0:                    image_root = label_path.split('/')[0]                    info[0]=os.path.join(image_root,info[0])                     self.data.append([info[0].strip(), info[1].strip()])    def preprocess(self,image):        """        数据增强函数        """        # 训练模式下的数据增强        if self.mode == 'train':            # 裁剪大小            image = image.resize((224, 224), Image.BICUBIC)             # 随机水平翻转                if random.randint(0, 1) == 1:                image = image.transpose(Image.FLIP_LEFT_RIGHT)            else:                pass            # 随机垂直翻转            if random.randint(0, 1) == 1:                image = image.transpose(Image.FLIP_TOP_BOTTOM)            else:                pass            # 图像归一化            image = np.asarray(image)            image = image.astype('float32')            mean = [0.485, 0.456, 0.406]            std = [0.229, 0.224, 0.225]            max_value = [255, 255, 255]            min_value = [0, 0, 0]            mean = np.asarray(mean, dtype=np.float32)[np.newaxis, np.newaxis, :]            std = np.asarray(std, dtype=np.float32)[np.newaxis, np.newaxis, :]            range_value = np.asarray([1. / (max_value[i] - min_value[i]) for i in range(len(max_value))],dtype=np.float32)            image = (image - np.asarray(min_value, dtype=np.float32)) * range_value            image -= mean            image /= std            # 数据格式转换            return paddle.to_tensor(image.transpose((2,0,1)))        # 验证和测试模型下的数据增强        else:            # 裁剪大小            image = image.resize((224, 224), Image.BICUBIC)              # 图像归一化            image = np.asarray(image)            image = image.astype('float32')            mean = [0.485, 0.456, 0.406]            std = [0.229, 0.224, 0.225]            max_value = [255, 255, 255]            min_value = [0, 0, 0]            mean = np.asarray(mean, dtype=np.float32)[np.newaxis, np.newaxis, :]            std = np.asarray(std, dtype=np.float32)[np.newaxis, np.newaxis, :]            range_value = np.asarray([1. / (max_value[i] - min_value[i]) for i in range(len(max_value))],dtype=np.float32)            image = (image - np.asarray(min_value, dtype=np.float32)) * range_value            image -= mean            image /= std            # 数据格式转换            return paddle.to_tensor(image.transpose((2,0,1)))    def __getitem__(self, index):        """        根据索引获取单个样本        """        image_file, label = self.data[index]        image = Image.open(image_file)        # 图片通道对齐        if image.mode != 'RGB':            image = image.convert('RGB')        # 进行数据增强        image = self.preprocess(image)        return image, np.array(label, dtype='int64')    def __len__(self):        """        获取样本总数        """        return len(self.data)

实例化数据集

In [4]

train_dataset=RESISC45Dataset(mode='train', label_path='NWPU-RESISC45/train_list.txt')val_dataset=RESISC45Dataset(mode='eval',label_path='NWPU-RESISC45/val_list.txt')test_dataset=RESISC45Dataset(mode='test',label_path='NWPU-RESISC45/test_list.txt')

模型搭建

这里搭建的模型是ResNet50，论文地址：Deep_Residual_Learning_for_Image_Recognition

ResNet介绍

ResNet（Residual Neural Network）由微软研究院的Kaiming He等四名华人提出，通过使用ResNet Unit成功训练出了152层的神经网络，并在ILSVRC2015比赛中取得冠军，在top5上的错误率为3.57%，同时参数量比VGGNet低，效果非常突出。ResNet的结构可以极快的加速神经网络的训练，模型的准确率也有比较大的提升。同时ResNet的推广性非常好，甚至可以直接用到InceptionNet网络中。

代码实现

In [13]

import paddleimport paddle.nn as nnfrom paddle.nn import Conv2D, MaxPool2D, AdaptiveAvgPool2D, Linear, ReLU, BatchNorm2Dimport paddle.nn.functional as F# 定义卷积批归一化块class ConvBNLayer(paddle.nn.Layer):    def __init__(self,                 in_channels,                 out_channels,                 kernel_size,                 stride=1,                 act=None):        super(ConvBNLayer, self).__init__()        # 创建卷积层        self._conv = Conv2D(            in_channels=in_channels,            out_channels=out_channels,            kernel_size=kernel_size,            stride=stride,            padding=(kernel_size - 1) // 2,            bias_attr=False)        # 创建BatchNorm层        self._batch_norm = BatchNorm2D(out_channels)        # 创建activate层        self.act = act    def forward(self, inputs):        y = self._conv(inputs)        y = self._batch_norm(y)        if self.act == 'relu':            y = F.relu(x=y)        return y        # 定义残差块class Bottleneckblock(paddle.nn.Layer):    def __init__(self, inplane, in_channel, out_channel, stride = 1, start = False):        super(Bottleneckblock, self).__init__()        self.stride = stride        self.start = start        self.conv0 = ConvBNLayer(in_channel, inplane, 1, stride = stride, act='relu')        self.conv1 = ConvBNLayer(inplane, inplane, 3, stride=1, act='relu')        self.conv2 = ConvBNLayer(inplane, out_channel, 1, stride=1, act=None)        self.conv3 = ConvBNLayer(in_channel, out_channel, 1, stride = stride, act=None)        self.relu = nn.ReLU()    def forward(self, inputs):        y = inputs        x = self.conv0(inputs)        x = self.conv1(x)        x = self.conv2(x)        if self.start:            y = self.conv3(y)        z = self.relu(x+y)        return zclass Resnet50(paddle.nn.Layer):    def __init__(self, num_classes=45):        super().__init__()        # stem layers        self.stem = nn.Sequential(                    nn.Conv2D(3, out_channels=64, kernel_size=7, stride=2, padding=3),                    nn.BatchNorm2D(64),                    nn.ReLU(),                    nn.MaxPool2D(kernel_size=3, stride=2, padding=1))        # blocks        self.layer1 = self.add_bottleneck_layer(3, 64, start = True)        self.layer2 = self.add_bottleneck_layer(4, 128)        self.layer3 = self.add_bottleneck_layer(6, 256)        self.layer4 = self.add_bottleneck_layer(3, 512)        # head layer        self.avgpool = nn.AdaptiveAvgPool2D(1)        self.classifier = nn.Linear(2048, num_classes)    def add_bottleneck_layer(self, num, inplane, start = False):        layer = []        if start:            layer.append(Bottleneckblock(inplane, inplane, inplane*4, start = True))        else:            layer.append(Bottleneckblock(inplane, inplane*2, inplane*4, stride = 2, start = True))        for i in range(num-1):            layer.append(Bottleneckblock(inplane, inplane*4, inplane*4))        return nn.Sequential(*layer)    def forward(self, inputs):        x = self.stem(inputs)        x = self.layer1(x)        x = self.layer2(x)        x = self.layer3(x)        x = self.layer4(x)                x = self.avgpool(x)        x = x.flatten(1)        x = self.classifier(x)        return x

实例化Resnet50并打印模型结构

In [14]

resnet50 = Resnet50(num_classes=45)

W0310 10:31:31.892053   141 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 11.0, Runtime API Version: 10.1W0310 10:31:31.896260   141 device_context.cc:465] device: 0, cuDNN Version: 7.6.

       In [15]

paddle.summary(resnet50, (1, 3, 224, 224))

-------------------------------------------------------------------------------   Layer (type)         Input Shape          Output Shape         Param #    ===============================================================================     Conv2D-1        [[1, 3, 224, 224]]   [1, 64, 112, 112]        9,472        BatchNorm2D-1    [[1, 64, 112, 112]]   [1, 64, 112, 112]         256            ReLU-1        [[1, 64, 112, 112]]   [1, 64, 112, 112]          0           MaxPool2D-1     [[1, 64, 112, 112]]    [1, 64, 56, 56]           0            Conv2D-2        [[1, 64, 56, 56]]     [1, 64, 56, 56]         4,096        BatchNorm2D-2     [[1, 64, 56, 56]]     [1, 64, 56, 56]          256         ConvBNLayer-1     [[1, 64, 56, 56]]     [1, 64, 56, 56]           0            Conv2D-3        [[1, 64, 56, 56]]     [1, 64, 56, 56]        36,864        BatchNorm2D-3     [[1, 64, 56, 56]]     [1, 64, 56, 56]          256         ConvBNLayer-2     [[1, 64, 56, 56]]     [1, 64, 56, 56]           0            Conv2D-4        [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384        BatchNorm2D-4     [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024        ConvBNLayer-3     [[1, 64, 56, 56]]     [1, 256, 56, 56]          0            Conv2D-5        [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384        BatchNorm2D-5     [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024        ConvBNLayer-4     [[1, 64, 56, 56]]     [1, 256, 56, 56]          0             ReLU-2         [[1, 256, 56, 56]]    [1, 256, 56, 56]          0        Bottleneckblock-1   [[1, 64, 56, 56]]     [1, 256, 56, 56]          0            Conv2D-6        [[1, 256, 56, 56]]    [1, 64, 56, 56]        16,384        BatchNorm2D-6     [[1, 64, 56, 56]]     [1, 64, 56, 56]          256         ConvBNLayer-5     [[1, 256, 56, 56]]    [1, 64, 56, 56]           0            Conv2D-7        [[1, 64, 56, 56]]     [1, 64, 56, 56]        36,864        BatchNorm2D-7     [[1, 64, 56, 56]]     [1, 64, 56, 56]          256         ConvBNLayer-6     [[1, 64, 56, 56]]     [1, 64, 56, 56]           0            Conv2D-8        [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384        BatchNorm2D-8     [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024        ConvBNLayer-7     [[1, 64, 56, 56]]     [1, 256, 56, 56]          0             ReLU-3         [[1, 256, 56, 56]]    [1, 256, 56, 56]          0        Bottleneckblock-2   [[1, 256, 56, 56]]    [1, 256, 56, 56]          0            Conv2D-10       [[1, 256, 56, 56]]    [1, 64, 56, 56]        16,384       BatchNorm2D-10     [[1, 64, 56, 56]]     [1, 64, 56, 56]          256         ConvBNLayer-9     [[1, 256, 56, 56]]    [1, 64, 56, 56]           0            Conv2D-11       [[1, 64, 56, 56]]     [1, 64, 56, 56]        36,864       BatchNorm2D-11     [[1, 64, 56, 56]]     [1, 64, 56, 56]          256        ConvBNLayer-10     [[1, 64, 56, 56]]     [1, 64, 56, 56]           0            Conv2D-12       [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384       BatchNorm2D-12     [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024       ConvBNLayer-11     [[1, 64, 56, 56]]     [1, 256, 56, 56]          0             ReLU-4         [[1, 256, 56, 56]]    [1, 256, 56, 56]          0        Bottleneckblock-3   [[1, 256, 56, 56]]    [1, 256, 56, 56]          0            Conv2D-14       [[1, 256, 56, 56]]    [1, 128, 28, 28]       32,768       BatchNorm2D-14     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-13     [[1, 256, 56, 56]]    [1, 128, 28, 28]          0            Conv2D-15       [[1, 128, 28, 28]]    [1, 128, 28, 28]       147,456      BatchNorm2D-15     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-14     [[1, 128, 28, 28]]    [1, 128, 28, 28]          0            Conv2D-16       [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536       BatchNorm2D-16     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048       ConvBNLayer-15     [[1, 128, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-17       [[1, 256, 56, 56]]    [1, 512, 28, 28]       131,072      BatchNorm2D-17     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048       ConvBNLayer-16     [[1, 256, 56, 56]]    [1, 512, 28, 28]          0             ReLU-5         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0        Bottleneckblock-4   [[1, 256, 56, 56]]    [1, 512, 28, 28]          0            Conv2D-18       [[1, 512, 28, 28]]    [1, 128, 28, 28]       65,536       BatchNorm2D-18     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-17     [[1, 512, 28, 28]]    [1, 128, 28, 28]          0            Conv2D-19       [[1, 128, 28, 28]]    [1, 128, 28, 28]       147,456      BatchNorm2D-19     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-18     [[1, 128, 28, 28]]    [1, 128, 28, 28]          0            Conv2D-20       [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536       BatchNorm2D-20     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048       ConvBNLayer-19     [[1, 128, 28, 28]]    [1, 512, 28, 28]          0             ReLU-6         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0        Bottleneckblock-5   [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-22       [[1, 512, 28, 28]]    [1, 128, 28, 28]       65,536       BatchNorm2D-22     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-21     [[1, 512, 28, 28]]    [1, 128, 28, 28]          0            Conv2D-23       [[1, 128, 28, 28]]    [1, 128, 28, 28]       147,456      BatchNorm2D-23     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-22     [[1, 128, 28, 28]]    [1, 128, 28, 28]          0            Conv2D-24       [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536       BatchNorm2D-24     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048       ConvBNLayer-23     [[1, 128, 28, 28]]    [1, 512, 28, 28]          0             ReLU-7         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0        Bottleneckblock-6   [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-26       [[1, 512, 28, 28]]    [1, 128, 28, 28]       65,536       BatchNorm2D-26     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-25     [[1, 512, 28, 28]]    [1, 128, 28, 28]          0            Conv2D-27       [[1, 128, 28, 28]]    [1, 128, 28, 28]       147,456      BatchNorm2D-27     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512        ConvBNLayer-26     [[1, 128, 28, 28]]    [1, 128, 28, 28]          0            Conv2D-28       [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536       BatchNorm2D-28     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048       ConvBNLayer-27     [[1, 128, 28, 28]]    [1, 512, 28, 28]          0             ReLU-8         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0        Bottleneckblock-7   [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-30       [[1, 512, 28, 28]]    [1, 256, 14, 14]       131,072      BatchNorm2D-30     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-29     [[1, 512, 28, 28]]    [1, 256, 14, 14]          0            Conv2D-31       [[1, 256, 14, 14]]    [1, 256, 14, 14]       589,824      BatchNorm2D-31     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-30     [[1, 256, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-32       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144      BatchNorm2D-32    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096       ConvBNLayer-31     [[1, 256, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-33       [[1, 512, 28, 28]]   [1, 1024, 14, 14]       524,288      BatchNorm2D-33    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096       ConvBNLayer-32     [[1, 512, 28, 28]]   [1, 1024, 14, 14]          0             ReLU-9        [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0        Bottleneckblock-8   [[1, 512, 28, 28]]   [1, 1024, 14, 14]          0            Conv2D-34      [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144      BatchNorm2D-34     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-33    [[1, 1024, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-35       [[1, 256, 14, 14]]    [1, 256, 14, 14]       589,824      BatchNorm2D-35     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-34     [[1, 256, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-36       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144      BatchNorm2D-36    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096       ConvBNLayer-35     [[1, 256, 14, 14]]   [1, 1024, 14, 14]          0             ReLU-10       [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0        Bottleneckblock-9  [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-38      [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144      BatchNorm2D-38     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-37    [[1, 1024, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-39       [[1, 256, 14, 14]]    [1, 256, 14, 14]       589,824      BatchNorm2D-39     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-38     [[1, 256, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-40       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144      BatchNorm2D-40    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096       ConvBNLayer-39     [[1, 256, 14, 14]]   [1, 1024, 14, 14]          0             ReLU-11       [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0       Bottleneckblock-10  [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-42      [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144      BatchNorm2D-42     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-41    [[1, 1024, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-43       [[1, 256, 14, 14]]    [1, 256, 14, 14]       589,824      BatchNorm2D-43     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-42     [[1, 256, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-44       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144      BatchNorm2D-44    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096       ConvBNLayer-43     [[1, 256, 14, 14]]   [1, 1024, 14, 14]          0             ReLU-12       [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0       Bottleneckblock-11  [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-46      [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144      BatchNorm2D-46     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-45    [[1, 1024, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-47       [[1, 256, 14, 14]]    [1, 256, 14, 14]       589,824      BatchNorm2D-47     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-46     [[1, 256, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-48       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144      BatchNorm2D-48    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096       ConvBNLayer-47     [[1, 256, 14, 14]]   [1, 1024, 14, 14]          0             ReLU-13       [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0       Bottleneckblock-12  [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-50      [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144      BatchNorm2D-50     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-49    [[1, 1024, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-51       [[1, 256, 14, 14]]    [1, 256, 14, 14]       589,824      BatchNorm2D-51     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024       ConvBNLayer-50     [[1, 256, 14, 14]]    [1, 256, 14, 14]          0            Conv2D-52       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144      BatchNorm2D-52    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096       ConvBNLayer-51     [[1, 256, 14, 14]]   [1, 1024, 14, 14]          0             ReLU-14       [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0       Bottleneckblock-13  [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-54      [[1, 1024, 14, 14]]     [1, 512, 7, 7]        524,288      BatchNorm2D-54      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048       ConvBNLayer-53    [[1, 1024, 14, 14]]     [1, 512, 7, 7]           0            Conv2D-55        [[1, 512, 7, 7]]      [1, 512, 7, 7]       2,359,296     BatchNorm2D-55      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048       ConvBNLayer-54      [[1, 512, 7, 7]]      [1, 512, 7, 7]           0            Conv2D-56        [[1, 512, 7, 7]]     [1, 2048, 7, 7]       1,048,576     BatchNorm2D-56     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192       ConvBNLayer-55      [[1, 512, 7, 7]]     [1, 2048, 7, 7]           0            Conv2D-57      [[1, 1024, 14, 14]]    [1, 2048, 7, 7]       2,097,152     BatchNorm2D-57     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192       ConvBNLayer-56    [[1, 1024, 14, 14]]    [1, 2048, 7, 7]           0             ReLU-15        [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0       Bottleneckblock-14  [[1, 1024, 14, 14]]    [1, 2048, 7, 7]           0            Conv2D-58       [[1, 2048, 7, 7]]      [1, 512, 7, 7]       1,048,576     BatchNorm2D-58      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048       ConvBNLayer-57     [[1, 2048, 7, 7]]      [1, 512, 7, 7]           0            Conv2D-59        [[1, 512, 7, 7]]      [1, 512, 7, 7]       2,359,296     BatchNorm2D-59      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048       ConvBNLayer-58      [[1, 512, 7, 7]]      [1, 512, 7, 7]           0            Conv2D-60        [[1, 512, 7, 7]]     [1, 2048, 7, 7]       1,048,576     BatchNorm2D-60     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192       ConvBNLayer-59      [[1, 512, 7, 7]]     [1, 2048, 7, 7]           0             ReLU-16        [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0       Bottleneckblock-15   [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0            Conv2D-62       [[1, 2048, 7, 7]]      [1, 512, 7, 7]       1,048,576     BatchNorm2D-62      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048       ConvBNLayer-61     [[1, 2048, 7, 7]]      [1, 512, 7, 7]           0            Conv2D-63        [[1, 512, 7, 7]]      [1, 512, 7, 7]       2,359,296     BatchNorm2D-63      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048       ConvBNLayer-62      [[1, 512, 7, 7]]      [1, 512, 7, 7]           0            Conv2D-64        [[1, 512, 7, 7]]     [1, 2048, 7, 7]       1,048,576     BatchNorm2D-64     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192       ConvBNLayer-63      [[1, 512, 7, 7]]     [1, 2048, 7, 7]           0             ReLU-17        [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0       Bottleneckblock-16   [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0       AdaptiveAvgPool2D-1  [[1, 2048, 7, 7]]     [1, 2048, 1, 1]           0            Linear-1           [[1, 2048]]            [1, 45]            92,205     ===============================================================================Total params: 23,653,421Trainable params: 23,547,181Non-trainable params: 106,240-------------------------------------------------------------------------------Input size (MB): 0.57Forward/backward pass size (MB): 328.09Params size (MB): 90.23Estimated Total Size (MB): 418.89-------------------------------------------------------------------------------

{'total_params': 23653421, 'trainable_params': 23547181}

模型训练

训练准备

In [22]

from paddle.optimizer import Momentumfrom paddle.optimizer.lr import CosineAnnealingDecayfrom paddle.regularizer import L2Decayfrom paddle.nn import CrossEntropyLossfrom paddle.metric import Accuracyimport math# 总训练轮数Epochs = 30# 数据集读取的批次大小Batch_size = 64# 每轮的训练步数Step_each_epoch = math.ceil(len(train_dataset.data)/Batch_size)# 配置学习率Lr=CosineAnnealingDecay(learning_rate=0.06, T_max=Step_each_epoch * Epochs)# 配置优化器Optimizer = Momentum(learning_rate=Lr,                     momentum=0.9,                     weight_decay=L2Decay(1e-4),                     parameters=resnet50.parameters())# 设置损失函数Loss_fn = CrossEntropyLoss()# 构建数据读取器                     Train_loader = paddle.io.DataLoader(train_dataset, batch_size=Batch_size, shuffle=True)Val_loader = paddle.io.DataLoader(val_dataset, batch_size=Batch_size)

正式训练

In [11]

def train(model, epochs, train_loader, val_loader, optimizer, loss_fn):    '''    训练函数    '''    acc_history = [0]    for epoch in range(epochs):        model.train() # 训练模式        for batch_id, data in enumerate(train_loader()): # 读取批次数据            x_data = data[0]            # 训练数据            y_data = data[1]            # 训练数据标签            y_data = paddle.reshape(y_data, (-1, 1))                        predicts = model(x_data)    # 预测结果            loss = loss_fn(predicts, y_data) # 计算损失            loss.backward() # 反向传播            optimizer.step() # 更新参数            optimizer.clear_grad() # 梯度清零        print("[TRAIN] epoch: {}/{}, loss is: {}".format(epoch+1, epochs, loss.numpy()))        model.eval() # 验证模式        loss_list = []        acc_list = []        for batch_id, data in enumerate(val_loader()): # 读取批次数据            x_data = data[0]            # 验证数据            y_data = data[1]            # 验证数据标签            y_data = paddle.reshape(y_data, (-1, 1))            predicts = model(x_data)    # 预测结果            loss = loss_fn(predicts, y_data) # 计算损失            acc = paddle.metric.accuracy(predicts, y_data) # 计算精度            loss_list.append(np.mean(loss.numpy()))            acc_list.append(np.mean(acc.numpy()))        print("[EVAL] Finished, Epoch={}, loss={}, acc={}".format(epoch+1, np.mean(loss_list), np.mean(acc_list)))        if acc_history[-1] < np.mean(acc_list):            paddle.save(resnet50.state_dict(),'output/resnet50.pdparams'.format(epoch))        acc_history.append(np.mean(acc_list))

   In [16]

# 进行训练train(resnet50, Epochs, Train_loader, Val_loader, Optimizer, Loss_fn)

模型验证

通过下面的代码可以看出我们的模型达到了0.83左右的精度

In [12]

def val(model, val_loader):    '''    验证函数    '''    model.eval() #验证模式    acc_list = []    for batch_id, data in enumerate(val_loader()):        x_data = data[0]            # 验证数据        y_data = data[1]            # 验证数据标签        y_data = paddle.reshape(y_data, (-1, 1))        predicts = model(x_data)    # 预测结果        acc = paddle.metric.accuracy(predicts, y_data) # 计算精度        acc_list.append(np.mean(acc.numpy()))    print("Eval finished, acc={}".format(np.mean(acc_list)))

   In [13]

# 加载保存的模型resnet50.set_state_dict(paddle.load('output/resnet50.pdparams'))# 进行验证val(resnet50,Val_loader)

Eval finished, acc=0.8262536525726318

模型预测

我们将模型预测的标签结果存入列表results下。

In [14]

def test(model, test_loader):    model.eval()    result_list = []    for batch_id, data in enumerate(test_loader()):        x_data = data[0] # 测试数据        predicts = model(x_data) # 测试数据标签        result_list.append(np.argmax(predicts.numpy(),axis=1)) # 存入列表    print("predict finished")    return result_list

   In [15]

# 加载测试数据集Test_loader = paddle.io.DataLoader(test_dataset, batch_size=64)# 加载保存的模型resnet50.set_state_dict(paddle.load('output/resnet50.pdparams'))# 进行预测results = test(resnet50,Test_loader)

predict finished

效果展示

In [18]

# 导入包%matplotlib inlineimport numpy as npimport cv2import matplotlib.pyplot as plt# 搭建label.txt的映射列表test_list = []with open('NWPU-RESISC45/labels.txt', 'r') as labels:    for line in labels:        test_list.append(line.strip())# 画图fig, axs = plt.subplots(nrows=5, ncols=1,figsize=(20,20))for i in range(5):    img = cv2.imread(test_dataset.data[i+10][0],1) # 读取图片    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # 通道转换    ax = axs[i]    ax.get_yaxis().set_visible(False)    ax.get_xaxis().set_visible(False)    ax.imshow(img) #展示图片    ax.set_title('Real: %s n Predict: %s'%(test_list[i+10],test_list[results[0][i+10]])) #展示原先标签和预测结果

以上就是【遥感影像分类】使用PaddleAPI搭建ResNet50实现遥感影像分类任务的详细内容，更多请关注创想鸟其它相关文章！