CT图片分类&神经网络

CT图片分类

链接：https://pan.baidu.com/s/15CxZVg_3L466hkpgeQ7-VA
提取码：dwck
ct图片的链接

from PIL import Image#图像进行操作
import matplotlib.pyplot as plt#绘图
import numpy as np#处理数组、效率很高
import os#处理文件、读文件
import tensorflow as tf
from tensorflow.keras import datasets, layers, models#kears是一个高级api

加载图片

加载livergate

X_train = Image.open('C:/Users/31035/Desktop/Desktop/data/livergate/livergate_0.png')
X_train = X_train.resize((512,512),Image.ANTIALIAS)
X_train = np.array(X_train)
X_train = np.expand_dims(X_train, axis=0)
print(X_train.shape)
for dirname, _, filenames in os.walk('C:/Users/31035/Desktop/Desktop/data/livergate'):
    for filename in filenames:
        if X_train.shape[0] > 357:
            break
        try:
            im = Image.open(os.path.join(dirname, filename))
            im = im.resize((512,512),Image.ANTIALIAS)
            image_array = np.array(im)
            image_array = np.expand_dims(image_array, axis=0)
            X_train = np.concatenate((X_train, image_array), axis=0)
        except:
            pass
print(str(X_train.shape[0]))

加载nolivergate、

X_train_n = Image.open('C:/Users/31035/Desktop/Desktop/data/nolivergate/other_0.png')
X_train_n = X_train_n.resize((512,512),Image.ANTIALIAS)
X_train_n = np.array(X_train_n)
X_train_n = np.expand_dims(X_train_n, axis=0)
print(X_train_n.shape)

for dirname, _, filenames in os.walk('C:/Users/31035/Desktop/Desktop/data/nolivergate'):
    for filename in filenames:
        if X_train_n.shape[0] > 820:
            break
        try:
            im = Image.open(os.path.join(dirname, filename))
            im = im.resize((512,512),Image.ANTIALIAS)
            image_array = np.array(im)
            image_array = np.expand_dims(image_array, axis=0)
            X_train_n = np.concatenate((X_train_n, image_array), axis=0)
        except:
            pass
print(X_train_n.shape)

设置标签

Y_train = np.ones((358))
Y_train = Y_train.astype(int)
Y_train_n = np.zeros((821))
Y_train_n = Y_train_n.astype(int)

合并数据后打乱

#如果不把数据集打乱，特征、标签集中，验证集效率会很低
X = np.concatenate((X_train,X_train_n),axis=0)
Y = np.concatenate((Y_train,Y_train_n),axis=0)
np.random.seed(200)
np.random.shuffle(X)
np.random.seed(200)
np.random.shuffle(Y)
X.shape,X.dtype

展示图片

class_names = ['nolivergate','livergate']

plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(X[i])
        plt.xlabel(class_names[Y[i]])
plt.show()

数据集后续处理

#给数据集增加一个维度，方便后面神经网络处理
X = tf.expand_dims(input=X,axis=-1)
#归一化，在这里归一化可以省略
X/255
#分离训练测试集
X_tra = X[:800]
X_test = X[800:]
y_tra = Y[:800]
Y_test = Y[800:]

建模分析预测

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(512,512,1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))

model.add(layers.Flatten()) # 3维 转为 1维
model.add(layers.Dense(64, activation='relu'))  # 激活函数relu
model.add(layers.Dense(2, activation='softmax'))  # 激活函数softmax CIFAR有10个类别输出，所以softmax这里参数设置为10
# 再看看模型情况
model.summary()

fit的一些参数

# fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, 
#     validation_data, shuffle, class_weight, sample_weight, initial_epoch, 
#     steps_per_epoch, validation_steps, validation_freq, max_queue_size, 
#     workers, use_multiprocessing, **kwargs)

编译和训练

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
history = model.fit(X_tra, y_tra,batch_size=20, epochs=10,
                    validation_data=(X_test, Y_test))

训练结果

用pd建个表

import pandas as pd
hist = pd.DataFrame(history.history)
hist['epoch'] = history.epoch
hist.tail()

绘制acc&loss折线图

def plot_history(history):
  hist = pd.DataFrame(history.history)
  hist['epoch'] = history.epoch

  plt.figure()
  plt.xlabel('Epoch')
  plt.ylabel('loss_value')
  plt.plot(hist['epoch'], hist['loss'],
           label='Train Loss')
  plt.plot(hist['epoch'], hist['val_loss'],
           label = 'Val Loss')
  plt.ylim([0,5])
  plt.legend()

  plt.figure()
  plt.xlabel('Epoch')
  plt.ylabel('acc_value')
  plt.plot(hist['epoch'], hist['accuracy'],
           label='Train acc')
  plt.plot(hist['epoch'], hist['val_accuracy'],
           label = 'Val acc')
#   plt.ylim([0,20])
  plt.legend()
  plt.show()

plot_history(history)