说明
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。
说明：
如今近视已经成为困扰人们健康的一项全球性负担，在近视人群中，有超过35%的人患有重度近视。近似将会导致眼睛的光轴被拉长，有可能引起视网膜或者络网膜的病变。随着近似度数的不断加深，高度近似有可能引发病理性病变，这将会导致以下几种症状：视网膜或者络网膜发生退化、视盘区域萎缩、漆裂样纹损害、Fuchs斑等。因此及早发现近似患者眼睛的病变并采取治疗，显得非常重要。
数据集准备
training.zip：包含训练中的图片和标签
validation.zip：包含验证集的图片
valid_gt.zip：包含验证集的标签
部分代码：
import os
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
from PIL import Image
DATADIR = '/home/aistudio/work/palm/PALM-Training400/PALM-Training400'
# 文件名以N开头的是正常眼底图片，以P开头的是病变眼底图片
file1 = 'N0012.jpg'
file2 = 'P0095.jpg'
# 读取图片
img1 = Image.open(os.path.join(DATADIR, file1))
img1 = np.array(img1)
img2 = Image.open(os.path.join(DATADIR, file2))
img2 = np.array(img2)
# 画出读取的图片
plt.figure(figsize=(16, 8))
f = plt.subplot(121)
f.set_title('Normal', fontsize=20)
plt.imshow(img1)
f = plt.subplot(122)
f.set_title('PM', fontsize=20)
plt.imshow(img2)
plt.show()# LeNet 识别眼疾图片
import os
import random
import paddle
import paddle.fluid as fluid
import numpy as np
DATADIR = '/home/aistudio/work/palm/PALM-Training400/PALM-Training400'
DATADIR2 = '/home/aistudio/work/palm/PALM-Validation400'
CSVFILE = '/home/aistudio/work/palm/PALM-Validation-GT/labels.csv'
# 定义训练过程
def train(model):
with fluid.dygraph.guard():
print('start training ... ')
model.train()
epoch_num = 5
# 定义优化器
opt = fluid.optimizer.Momentum(learning_rate=0.001, momentum=0.9, parameter_list=model.parameters())
# 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')
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 = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
# 运行模型前向计算，得到预测值
logits = model(img)
# 进行loss计算
loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label)
avg_loss = fluid.layers.mean(loss)
if batch_id % 10 == 0:
print("epoch: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, avg_loss.numpy()))
# 反向传播，更新权重，清除梯度
avg_loss.backward()
opt.minimize(avg_loss)
model.clear_gradients()
model.eval()
accuracies = []
losses = []
for batch_id, data in enumerate(valid_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
# 运行模型前向计算，得到预测值
logits = model(img)
# 二分类，sigmoid计算后的结果以0.5为阈值分两个类别
# 计算sigmoid后的预测概率，进行loss计算
pred = fluid.layers.sigmoid(logits)
loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label)
# 计算预测概率小于0.5的类别
pred2 = pred * (-1.0) + 1.0
# 得到两个类别的预测概率，并沿第一个维度级联
pred = fluid.layers.concat([pred2, pred], axis=1)
acc = fluid.layers.accuracy(pred, fluid.layers.cast(label, dtype='int64'))
accuracies.append(acc.numpy())
losses.append(loss.numpy())
print("[validation] accuracy/loss: {}/{}".format(np.mean(accuracies), np.mean(losses)))
model.train()
# save params of model
fluid.save_dygraph(model.state_dict(), 'mnist')
# save optimizer state
fluid.save_dygraph(opt.state_dict(), 'mnist')
# 定义评估过程
def evaluation(model, params_file_path):
with fluid.dygraph.guard():
print('start evaluation .......')
#加载模型参数
model_state_dict, _ = fluid.load_dygraph(params_file_path)
model.load_dict(model_state_dict)
model.eval()
eval_loader = load_data('eval')
acc_set = []
avg_loss_set = []
for batch_id, data in enumerate(eval_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
# 计算预测和精度
prediction, acc = model(img, label)
# 计算损失函数值
loss = fluid.layers.cross_entropy(input=prediction, label=label)
avg_loss = fluid.layers.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={}, acc={}'.format(avg_loss_val_mean, acc_val_mean))
# 导入需要的包
import paddle
import paddle.fluid as fluid
import numpy as np
from paddle.fluid.dygraph.nn import Conv2D, Pool2D, Linear
# 定义 LeNet 网络结构
class LeNet(fluid.dygraph.Layer):
def __init__(self, name_scope, num_classes=1):
super(LeNet, self).__init__(name_scope)
# 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(num_channels=3, num_filters=6, filter_size=5, act='sigmoid')
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv2 = Conv2D(num_channels=6, num_filters=16, filter_size=5, act='sigmoid')
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
# 创建第3个卷积层
self.conv3 = Conv2D(num_channels=16, num_filters=120, filter_size=4, act='sigmoid')
# 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裂标签的类别数
self.fc1 = Linear(input_dim=300000, output_dim=64, act='sigmoid')
self.fc2 = Linear(input_dim=64, output_dim=num_classes)
# 网络的前向计算过程
def forward(self, x):
x = self.conv1(x)
x = self.pool1(x)
x = self.conv2(x)
x = self.pool2(x)
x = self.conv3(x)
x = fluid.layers.reshape(x, [x.shape[0], -1])
x = self.fc1(x)
x = self.fc2(x)
return x
if __name__ == '__main__':
# 创建模型
with fluid.dygraph.guard():
model = LeNet("LeNet_", num_classes=1)
train(model)
