眼疾图片识别

# -*- coding = utf-8 -*-
# @Time : 2022/12/19 16:29

# @File ： VGG.py
# @File : PyCharm
# coding:utf-8
import os
import cv2
import random
import numpy as np
import paddle
from paddle.nn import Conv2D, MaxPool2D, Linear, BatchNorm2D
import paddle.nn.functional as F


# 图像预处理
def transform_img(img):
    img = cv2.resize(img, (224, 224))
    img = np.transpose(img, (2, 0, 1))
    img = img.astype('float32')
    img = img / 255.0
    img = img * 2.0 - 1.0
    return img


# 定义训练集数据读取器
def data_loader(datadir, batch_size=10, mode='train'):
    filenames = os.listdir(datadir)

    def reader():
        if mode == 'train':
            random.shuffle(filenames)
        batch_imgs = []
        batch_labels = []
        for name in filenames:
            filepath = os.path.join(datadir, name)
            img = cv2.imread(filepath)
            img = transform_img(img)
            if name[0] == 'H' or name[0] == 'N':
                label = 0
            elif name[0] == 'P':
                label = 1
            else:
                raise ('Not excepted file name')
            batch_imgs.append(img)
            batch_labels.append(label)
            if len(batch_imgs) == batch_size:
                imgs_array = np.array(batch_imgs).astype('float32')
                labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
                yield imgs_array, labels_array
                batch_imgs = []
                batch_labels = []
        if len(batch_imgs) > 0:
            imgs_array = np.array(batch_imgs).astype('float32')
            labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
            yield imgs_array, labels_array

    return reader


# 定义验证集数据读取器
def valid_data_loader(datadir, csvfile, batch_size=10, mode='valid'):
    filelists = open(csvfile).readlines()

    def reader():
        batch_imgs = []
        batch_labels = []
        for line in filelists[1:]:
            line = line.strip().split(',')
            if line[0] == '':
                break
            name = line[1]
            label = int(line[2])
            filepath = os.path.join(datadir, name)
            img = cv2.imread(filepath)
            img = transform_img(img)
            batch_imgs.append(img)
            batch_labels.append(label)
            if len(batch_imgs) == batch_size:
                imgs_array = np.array(batch_imgs).astype('float32')
                labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
                yield imgs_array, labels_array
                batch_imgs = []
                batch_labels = []
        if len(batch_imgs) > 0:
            imgs_array = np.array(batch_imgs).astype('float32')
            labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
            yield imgs_array, labels_array

    return reader

DATADIR = './data/PALM-Training400'
DATADIR2 = './data/PALM-Validation400'
CSVFILE = './data/labels.csv'

EPOCH_NUM = 20


def train_pm(model, optimizer):
    use_gpu = True
    paddle.set_device('gpu:0') if use_gpu else paddle.set_device('cpu')

    print('start training ...')
    model.train()
    train_loader = data_loader(DATADIR, batch_size=10, mode='train')
    valid_loader = valid_data_loader(DATADIR2, CSVFILE)
    for epoch in range(EPOCH_NUM):
        for batch_id, data in enumerate(train_loader()):
            x_data, y_data = data
            img = paddle.to_tensor(x_data)
            label = paddle.to_tensor(y_data)
            logits = model(img)
            loss = F.binary_cross_entropy_with_logits(logits, label)
            avg_loss = paddle.mean(loss)

            if batch_id % 20 == 0:
                print("epoch:{}, batch_id:{}, loss:{:.4f}".format(epoch + 1, batch_id, float(avg_loss.numpy())))

            avg_loss.backward()
            optimizer.step()
            optimizer.clear_grad()

        model.eval()
        accuracies = []
        losses = []
        for batch_id, data in enumerate(valid_loader()):
            x_data, y_data = data
            img = paddle.to_tensor(x_data)
            label = paddle.to_tensor(y_data)
            logits = model(img)
            pred = F.sigmoid(logits)
            loss = F.binary_cross_entropy_with_logits(logits, label)
            pred2 = pred * (-1.0) + 1.0
            pred = paddle.concat([pred2, pred], axis=1)
            acc = paddle.metric.accuracy(pred, paddle.cast(label, dtype='int64'))
            accuracies.append(acc.numpy())
            losses.append(loss.numpy())
        print("[validation] accuracy/loss: {:.4f}/{:.4f}".format(np.mean(accuracies), np.mean(losses)))
        model.train()

        paddle.save(model.state_dict(), 'palm.pdparams')
        paddle.save(optimizer.state_dict(), 'palm.pdopt')


class VGG(paddle.nn.Layer):
    def __init__(self):
        super(VGG, self).__init__()

        in_channels = [3, 64, 128, 256, 512, 512]

        self.conv1_1 = Conv2D(in_channels=in_channels[0], out_channels=in_channels[1], kernel_size=3, padding=1,
                              stride=1)
        self.conv1_2 = Conv2D(in_channels=in_channels[1], out_channels=in_channels[1], kernel_size=3, padding=1,
                              stride=1)

        self.conv2_1 = Conv2D(in_channels=in_channels[1], out_channels=in_channels[2], kernel_size=3, padding=1,
                              stride=1)
        self.conv2_2 = Conv2D(in_channels=in_channels[2], out_channels=in_channels[2], kernel_size=3, padding=1,
                              stride=1)

        self.conv3_1 = Conv2D(in_channels=in_channels[2], out_channels=in_channels[3], kernel_size=3, padding=1,
                              stride=1)
        self.conv3_2 = Conv2D(in_channels=in_channels[3], out_channels=in_channels[3], kernel_size=3, padding=1,
                              stride=1)
        self.conv3_3 = Conv2D(in_channels=in_channels[3], out_channels=in_channels[3], kernel_size=3, padding=1,
                              stride=1)

        self.conv4_1 = Conv2D(in_channels=in_channels[3], out_channels=in_channels[4], kernel_size=3, padding=1,
                              stride=1)
        self.conv4_2 = Conv2D(in_channels=in_channels[4], out_channels=in_channels[4], kernel_size=3, padding=1,
                              stride=1)
        self.conv4_3 = Conv2D(in_channels=in_channels[4], out_channels=in_channels[4], kernel_size=3, padding=1,
                              stride=1)

        self.conv5_1 = Conv2D(in_channels=in_channels[4], out_channels=in_channels[5], kernel_size=3, padding=1,
                              stride=1)
        self.conv5_2 = Conv2D(in_channels=in_channels[5], out_channels=in_channels[5], kernel_size=3, padding=1,
                              stride=1)
        self.conv5_3 = Conv2D(in_channels=in_channels[5], out_channels=in_channels[5], kernel_size=3, padding=1,
                              stride=1)

        self.fc1 = paddle.nn.Sequential(paddle.nn.Linear(512 * 7 * 7, 4096), paddle.nn.ReLU())
        self.drop1_ratio = 0.5
        self.dropout1 = paddle.nn.Dropout(self.drop1_ratio, mode='upscale_in_train')

        self.fc2 = paddle.nn.Sequential(paddle.nn.Linear(4096, 4096), paddle.nn.ReLU())

        self.drop2_ratio = 0.5
        self.dropout2 = paddle.nn.Dropout(self.drop2_ratio, mode='upscale_in_train')
        self.fc3 = paddle.nn.Linear(4096, 1)

        self.relu = paddle.nn.ReLU()
        self.pool = MaxPool2D(stride=2, kernel_size=2)

    def forward(self, x):
        x = self.relu(self.conv1_1(x))
        x = self.relu(self.conv1_2(x))
        x = self.pool(x)

        x = self.relu(self.conv2_1(x))
        x = self.relu(self.conv2_2(x))
        x = self.pool(x)

        x = self.relu(self.conv3_1(x))
        x = self.relu(self.conv3_2(x))
        x = self.relu(self.conv3_3(x))
        x = self.pool(x)

        x = self.relu(self.conv4_1(x))
        x = self.relu(self.conv4_2(x))
        x = self.relu(self.conv4_3(x))
        x = self.pool(x)

        x = self.relu(self.conv5_1(x))
        x = self.relu(self.conv5_2(x))
        x = self.relu(self.conv5_3(x))
        x = self.pool(x)

        x = paddle.flatten(x, 1, -1)
        x = self.dropout1(self.relu(self.fc1(x)))
        x = self.dropout2(self.relu(self.fc2(x)))
        x = self.fc3(x)
        return x


model = VGG()
opt = paddle.optimizer.Momentum(learning_rate=0.001, momentum=0.9, parameters=model.parameters())

train_pm(model, opt)

# -*- coding = utf-8 -*-
# @Time : 2022/12/18 9:50

# @File ： predict_Pathologic_Myopia.py
# @File : PyCharm
# coding:utf-8




#数据集介绍：
# iChallenge - PM是百度大脑和中山大学中山眼科中心联合举办的iChallenge比赛中，提供的关于病理性近视（Pathologic
# Myopia，PM）的医疗类数据集，包含1200个受试者的眼底视网膜图片，训练、验证和测试数据集各400张。

# iChallenge - PM中既有病理性近视患者的眼底图片，也有非病理性近视患者的图片，命名规则如下：
# 病理性近视（PM）：文件名以P开头
# 非病理性近视（non - PM）：
# 高度近似（high
# 正常眼睛（normal）：文件名以N开头
# 我们将病理性患者的图片作为正样本，标签为1； 非病理性患者的图片作为负样本，标签为0。

import os
import cv2
import random #随机打乱数据
import numpy as np
import paddle
from paddle.nn import Conv2D, MaxPool2D, Linear, BatchNorm2D#卷积网络 层
import paddle.nn.functional as F

# 1.对读入的图像进行预处理
def transform_img(img):
    #将图片尺寸缩放到224*224
    img = cv2.resize(img, (224, 224))
    # 读入的图像数据格式是[H,W,C]
    # 使用转置操作将其变成[C,H,W]，通道的调换顺序调换为RGB
    img = np.transpose(img, (2, 0, 1))
    #将每个元素转成float32
    img = img.astype('float32')
    # 将其数据范围调整到[-1.0,1.0]之间
    img = img / 255.0#[0,1]
    img = img * 2.0 - 1.0#[-1,1]
    return img


# 2.定义训练集数据读取器
def data_loader(datadir, batch_size=10, mode='train'):
    # 将datadir目录下文件列出来，每条文件都要读入
    filenames = os.listdir(datadir)

    def reader():
        if mode == 'train':
            # 将训练集的数据随机打乱
            random.shuffle(filenames)
        #两个list装每个batch中的数据与标签
        batch_imgs = []
        batch_labels = []
        for name in filenames:
            # 拼接出每张图片的完整路径
            filepath = os.path.join(datadir, name)
            # 调用cv2.imread来读取图片
            img = cv2.imread(filepath)
            # 图片进行预处理，来去得到这张图片他本身
            img = transform_img(img)
            if name[0] == 'H' or name[0] == 'N':
                # H开头的文件名表示高度近视，N开头的文件名表示视力正常
                # 高度近视与正常视力的样本，都不是病理性的，属于负样本，标签为0
                label = 0
            elif name[0] == 'P':
                # P开头的是病理性近视，属于正样本，标签为1
                label = 1
            else:
                raise('Not excepted file name')
            # 每读取一个样本的数据，就将其放入数据列表中
            batch_imgs.append(img)
            batch_labels.append(label)
            if len(batch_imgs) == batch_size:
                # 当数据列表的长度等于batch_imgs的时候，
                # 把这些数据当作一个mini-batch，并作为数据生成器的一个输出
                imgs_array = np.array(batch_imgs).astype('float32')
                labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
                yield imgs_array, labels_array
                batch_imgs = []
                batch_labels = []

        if len(batch_imgs) > 0:
            # 剩余样本数目不足一个batch_size的数据，一起打包成mini-batch
            imgs_array = np.array(batch_imgs).astype('float32')
            labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
            yield imgs_array, labels_array

    return reader

# 设置迭代轮数5
EPOCH_NUM = 5

#3.定义训练过程
def train_pm(model, optimizer):
    # 选择gpu或者cpu，此处gpu:0
    # use_gpu = True
    # paddle.set_device('gpu:0') if use_gpu else paddle.set_device('cpu')

    print('start training ...')
    model.train()
    # 定义数据读取器，训练数据读取器和验证数据读取器
    train_loader = data_loader(DATADIR, batch_size=10, mode='train')
    for epoch in range(EPOCH_NUM):
        for batch_id, data in enumerate(train_loader()):
            x_data, y_data = data
            img = paddle.to_tensor(x_data)
            label = paddle.to_tensor(y_data)
            # 运行模型前向计算，得到预测值
            logits = model(img)
            loss = F.binary_cross_entropy_with_logits(logits, label)
            avg_loss = paddle.mean(loss)

            if batch_id % 20 == 0:
                print("epoch:{}, batch_id:{}, loss:{:.4f}".format(epoch + 1, batch_id, float(avg_loss.numpy())))
            # 反向传播，更新权重，清除梯度
            avg_loss.backward()
            optimizer.step()
            optimizer.clear_grad()

        model.eval()
        accuracies = []
        losses = []
        valid_loader = data_loader(DATADIR, batch_size=10, mode='eval')
        # 分批次 验证
        for batch_id, data in enumerate(valid_loader()):
            x_data, y_data = data
            img = paddle.to_tensor(x_data)
            label = paddle.to_tensor(y_data)
            # 运行模型的前向计算，得到预测值
            logits = model(img)
            # 二分类，sigmoid计算后的记过以0.5为阈值分成两类
            # 计算sigmoid后的预测概率，进行loss计算
            pred = F.sigmoid(logits)
            loss = F.binary_cross_entropy_with_logits(logits, label)
            # 计算概率小于0.5的类别
            pred2 = pred * (-1.0) + 1.0
            # 得到两个类别（pred:正例，pred2:负例）的预测概率，并沿第一个维度级联
            pred = paddle.concat([pred2, pred], axis=1)
            acc = paddle.metric.accuracy(pred, paddle.cast(label, dtype='int64'))

            accuracies.append(acc.numpy())
            losses.append(loss.numpy())
        print("[validation] accuracy/loss: {:.4f}/{:.4f}".format(np.mean(accuracies), np.mean(losses)))
        model.train()

        # 保存模型中参数，保存优化器的参数
        paddle.save(model.state_dict(), 'palm.pdparams')
        paddle.save(optimizer.state_dict(), 'palm.pdopt')

#4.定义评估过程
def evaluation(model, params_file_path):

    # use_gpu = True
    # paddle.set_device('gpu:0') if use_gpu else paddle.set_device('cpu')

    print('start evaluation .......')
    #加载之前保存的模型参数
    model_state_dict = paddle.load(params_file_path)
    model.load_dict(model_state_dict)

    model.eval()
    # 调用data_loader，获取reader
    eval_loader = data_loader(DATADIR, batch_size=10, mode='eval')

    acc_set = []
    avg_loss_set = []
    for batch_id, data in enumerate(eval_loader()):
        x_data, y_data = data
        img = paddle.to_tensor(x_data)
        label = paddle.to_tensor(y_data)
        y_data = y_data.astype(np.int64)
        label_64 = paddle.to_tensor(y_data)
        # model.forward计算预测和精度
        prediction, acc = model(img, label_64)
        # 计算损失函数值
        loss = F.binary_cross_entropy_with_logits(prediction, label)

        avg_loss = paddle.mean(loss)
        acc_set.append(float(acc.numpy()))
        avg_loss_set.append(float(avg_loss.numpy()))
    # 求平均精度
    acc_val_mean = np.array(acc_set).mean()
    avg_loss_val_mean = np.array(avg_loss_set).mean()

    print('loss={:.4f}, acc={:.4f}'.format(avg_loss_val_mean, acc_val_mean))

# 定义 LeNet 网络结构
class LeNet(paddle.nn.Layer):
    def __init__(self, num_classes=1):
        super(LeNet, self).__init__()

        # 创建卷积和池化层块，每个卷积层使用Sigmoid激活函数，后面跟着一个2x2的池化
        self.conv1 = Conv2D(in_channels=3, out_channels=6, kernel_size=5)
        self.max_pool1 = MaxPool2D(kernel_size=2,stride=2)
        self.conv2 = Conv2D(in_channels=6, out_channels=16, kernel_size=5)
        self.max_pool2 = MaxPool2D(kernel_size=2,stride=2)
        # 创建第3个卷积层
        self.conv3 = Conv2D(in_channels=16, out_channels=120, kernel_size=4)
        # 创建全连接层，第一个全连接层的输出神经元个数为64， 第二个全连接层输出神经元个数为分类标签的类别数
        self.fc1 = Linear(in_features=300000, out_features=64)
        self.fc2 = Linear(in_features=64, out_features=num_classes)

    # 网络的前向计算过程，定义输出每一层的结果，
    # 后续将结果写入VisualDL日志文件，实现每一层输出图片的可视化
    def forward(self, x,label=None):
        x = self.conv1(x)
        x = F.sigmoid(x)
        x = self.max_pool1(x)
        x = self.conv2(x)
        x = F.sigmoid(x)
        x = self.max_pool2(x)
        x = self.conv3(x)
        x = F.sigmoid(x)
        x = paddle.reshape(x,[x.shape[0],-1])#做reshape连接全连接层
        x = self.fc1(x)
        x = F.sigmoid(x)
        x = self.fc2(x)
        if label is not None:
            acc = paddle.metric.accuracy(input=x,label=label)
            return x, acc
        else:
            return x

# 查看数据形状：
DATADIR = './data/PALM-Training400'
# 创建模型
model = LeNet(num_classes=1)
# 启动训练过程
opt = paddle.optimizer.Momentum(learning_rate=0.001, momentum=0.9, parameters=model.parameters())
train_pm(model,optimizer=opt)
evaluation(model, params_file_path="palm.pdparams")

# -*- coding = utf-8 -*-
# @Time : 2022/12/18 9:50

# @File ： predict_Pathologic_Myopia.py
# @File : PyCharm
# coding:utf-8

import os
import cv2
import random #随机打乱数据
import numpy as np
import paddle
from paddle import nn
from paddle.nn import Conv2D, MaxPool2D, Linear, BatchNorm2D, AdaptiveAvgPool2D, Dropout  # 卷积网络 层
import paddle.nn.functional as F

# 1.对读入的图像进行预处理
def transform_img(img):
    #将图片尺寸缩放到224*224
    img = cv2.resize(img, (224, 224))
    # 读入的图像数据格式是[H,W,C]
    # 使用转置操作将其变成[C,H,W]，通道的调换顺序调换为RGB
    img = np.transpose(img, (2, 0, 1))
    #将每个元素转成float32
    img = img.astype('float32')
    # 将其数据范围调整到[-1.0,1.0]之间
    img = img / 255.0#[0,1]
    img = img * 2.0 - 1.0#[-1,1]
    return img


# 2.定义训练集数据读取器
def data_loader(datadir, batch_size=10, mode='train'):
    # 将datadir目录下文件列出来，每条文件都要读入
    filenames = os.listdir(datadir)

    def reader():
        if mode == 'train':
            # 将训练集的数据随机打乱
            random.shuffle(filenames)
        #两个list装每个batch中的数据与标签
        batch_imgs = []
        batch_labels = []
        for name in filenames:
            # 拼接出每张图片的完整路径
            filepath = os.path.join(datadir, name)
            # 调用cv2.imread来读取图片
            img = cv2.imread(filepath)
            # 图片进行预处理，来去得到这张图片他本身
            img = transform_img(img)
            if name[0] == 'H' or name[0] == 'N':
                # H开头的文件名表示高度近视，N开头的文件名表示视力正常
                # 高度近视与正常视力的样本，都不是病理性的，属于负样本，标签为0
                label = 0
            elif name[0] == 'P':
                # P开头的是病理性近视，属于正样本，标签为1
                label = 1
            else:
                raise('Not excepted file name')
            # 每读取一个样本的数据，就将其放入数据列表中
            batch_imgs.append(img)
            batch_labels.append(label)
            if len(batch_imgs) == batch_size:
                # 当数据列表的长度等于batch_imgs的时候，
                # 把这些数据当作一个mini-batch，并作为数据生成器的一个输出
                imgs_array = np.array(batch_imgs).astype('float32')
                labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
                yield imgs_array, labels_array
                batch_imgs = []
                batch_labels = []

        if len(batch_imgs) > 0:
            # 剩余样本数目不足一个batch_size的数据，一起打包成mini-batch
            imgs_array = np.array(batch_imgs).astype('float32')
            labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
            yield imgs_array, labels_array

    return reader

# 设置迭代轮数5
EPOCH_NUM = 5

#3.定义训练过程
def train_pm(model, optimizer):
    # 选择gpu或者cpu，此处gpu:0
    # use_gpu = True
    # paddle.set_device('gpu:0') if use_gpu else paddle.set_device('cpu')

    print('start training ...')
    model.train()
    # 定义数据读取器，训练数据读取器和验证数据读取器
    train_loader = data_loader(DATADIR, batch_size=10, mode='train')
    for epoch in range(EPOCH_NUM):
        for batch_id, data in enumerate(train_loader()):
            x_data, y_data = data
            img = paddle.to_tensor(x_data)
            label = paddle.to_tensor(y_data)
            # 运行模型前向计算，得到预测值
            logits = model(img)
            loss = F.binary_cross_entropy_with_logits(logits, label)
            avg_loss = paddle.mean(loss)

            if batch_id % 20 == 0:
                print("epoch:{}, batch_id:{}, loss:{:.4f}".format(epoch + 1, batch_id, float(avg_loss.numpy())))
            # 反向传播，更新权重，清除梯度
            avg_loss.backward()
            optimizer.step()
            optimizer.clear_grad()

        model.eval()
        accuracies = []
        losses = []
        valid_loader = data_loader(DATADIR, batch_size=10, mode='eval')
        # 分批次 验证
        for batch_id, data in enumerate(valid_loader()):
            x_data, y_data = data
            img = paddle.to_tensor(x_data)
            label = paddle.to_tensor(y_data)
            # 运行模型的前向计算，得到预测值
            logits = model(img)
            # 二分类，sigmoid计算后的记过以0.5为阈值分成两类
            # 计算sigmoid后的预测概率，进行loss计算
            pred = F.sigmoid(logits)
            loss = F.binary_cross_entropy_with_logits(logits, label)
            # 计算概率小于0.5的类别
            pred2 = pred * (-1.0) + 1.0
            # 得到两个类别（pred:正例，pred2:负例）的预测概率，并沿第一个维度级联
            pred = paddle.concat([pred2, pred], axis=1)
            acc = paddle.metric.accuracy(pred, paddle.cast(label, dtype='int64'))

            accuracies.append(acc.numpy())
            losses.append(loss.numpy())
        print("[validation] accuracy/loss: {:.4f}/{:.4f}".format(np.mean(accuracies), np.mean(losses)))
        model.train()

        # 保存模型中参数，保存优化器的参数
        paddle.save(model.state_dict(), 'palm.pdparams')
        paddle.save(optimizer.state_dict(), 'palm.pdopt')

#4.定义评估过程
def evaluation(model, params_file_path):

    # use_gpu = True
    # paddle.set_device('gpu:0') if use_gpu else paddle.set_device('cpu')

    print('start evaluation .......')
    #加载之前保存的模型参数
    model_state_dict = paddle.load(params_file_path)
    model.load_dict(model_state_dict)

    model.eval()
    # 调用data_loader，获取reader
    eval_loader = data_loader(DATADIR, batch_size=10, mode='eval')

    acc_set = []
    avg_loss_set = []
    for batch_id, data in enumerate(eval_loader()):
        x_data, y_data = data
        img = paddle.to_tensor(x_data)
        label = paddle.to_tensor(y_data)
        y_data = y_data.astype(np.int64)
        label_64 = paddle.to_tensor(y_data)
        # model.forward计算预测和精度
        prediction, acc = model(img, label_64)
        # 计算损失函数值
        loss = F.binary_cross_entropy_with_logits(prediction, label)

        avg_loss = paddle.mean(loss)
        acc_set.append(float(acc.numpy()))
        avg_loss_set.append(float(avg_loss.numpy()))
    # 求平均精度
    acc_val_mean = np.array(acc_set).mean()
    avg_loss_val_mean = np.array(avg_loss_set).mean()

    print('loss={:.4f}, acc={:.4f}'.format(avg_loss_val_mean, acc_val_mean))






# 定义 AlexNet 网络结构
class AlexNet(paddle.nn.Layer):
    def __init__(self, num_classes=1):
        super(AlexNet, self).__init__()

        # AlexNet与LeNet一样也会同时使用卷积和池化层提取图像特征
        # 与LeNet不同的是激活函数换成了‘relu’
        self.conv1 = Conv2D(in_channels=3, out_channels=96, kernel_size=11, stride=4, padding=5)
        self.max_pool1 = MaxPool2D(kernel_size=2, stride=2)
        self.conv2 = Conv2D(in_channels=96, out_channels=256, kernel_size=5, stride=1, padding=2)
        self.max_pool2 = MaxPool2D(kernel_size=2, stride=2)
        self.conv3 = Conv2D(in_channels=256, out_channels=384, kernel_size=3, stride=1, padding=1)
        self.conv4 = Conv2D(in_channels=384, out_channels=384, kernel_size=3, stride=1, padding=1)
        self.conv5 = Conv2D(in_channels=384, out_channels=256, kernel_size=3, stride=1, padding=1)
        self.max_pool5 = MaxPool2D(kernel_size=2, stride=2)

        self.fc1 = Linear(in_features=12544, out_features=4096)
        self.drop_ratio1 = 0.5
        self.drop1 = Dropout(self.drop_ratio1)
        self.fc2 = Linear(in_features=4096, out_features=4096)
        self.drop_ratio2 = 0.5
        self.drop2 = Dropout(self.drop_ratio2)
        self.fc3 = Linear(in_features=4096, out_features=num_classes)

    # 网络的前向计算过程，定义输出每一层的结果，
    # 后续将结果写入VisualDL日志文件，实现每一层输出图片的可视化
    def forward(self, x,label=None):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.max_pool1(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = self.max_pool2(x)
        x = self.conv3(x)
        x = F.relu(x)
        x = self.conv4(x)
        x = F.relu(x)
        x = self.conv5(x)
        x = F.relu(x)
        x = self.max_pool5(x)
        x = paddle.reshape(x,[x.shape[0],-1])#做reshape连接全连接层
        x = self.fc1(x)
        x = F.relu(x)
        # 在全连接之后使用dropout抑制过拟合
        x = self.drop1(x)
        x = self.fc2(x)
        x = F.relu(x)
        # 在全连接之后使用dropout抑制过拟合
        x = self.drop2(x)
        x = self.fc3(x)
        if label is not None:
            acc = paddle.metric.accuracy(input=x, label=label)
            return x, acc
        else:
            return x


# 数据集所在文件:
DATADIR = './data/PALM-Training400'

# 创建模型
model = AlexNet(num_classes=1)


# 启动训练过程
opt = paddle.optimizer.Momentum(learning_rate=0.001, momentum=0.9, parameters=model.parameters())
train_pm(model,optimizer=opt)#训练模型
evaluation(model, params_file_path="palm.pdparams")#评估模型