Skin cancer classification-based on Keras convolutional neural network to achieve classification

Skin cancer classification-based on Keras convolutional neural network to achieve classification

The pathological pictures in the data set contain 3 categories
melanoma (melanoma) nevus (nevi) seborrheickeratosis (seborrheic keratosis)

from sklearn import datasets
import numpy as np
import pandas as pd
import os
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from keras.preprocessing import image as image2
from tqdm import tqdm
from PIL import ImageFile
plt.style.use('default')
from matplotlib import image
def plot_image(filename_list):
    fig,axes=plt.subplots(nrows=3,ncols=3)
    fig.set_size_inches(10,9)
    random_9_nums=np.random.choice(len(filename_list),9)
    random_9_imgs=filename_list[random_9_nums]
    print(random_9_imgs)
    imgname_list=[]
    for imgpath in random_9_imgs:
        imgname=imgpath[len(datasets_path)+1:]
        imgname=imgname[:imgname.find('/')]
        imgname_list.append(imgname)
    index=0
    for row_index in range(3):
        for col_index in range(3):
            img=image.imread(random_9_imgs[index])
            ax=axes[row_index,col_index]
            ax.imshow(img)
            ax.set_xlabel(imgname_list[index])
            index+=1
    plt.show()
    print("查看病理图片的大小：")

    for i, img_path in enumerate(random_9_imgs):
        print_img_shape(i, img_path)
def get_data(path):
    data=datasets.load_files(path)
    return data
def print_img_shape(i,filepath):
    shape=image.imread(filepath).shape
    print("第{}张的shape是{}".format(i+1,shape))
def path_to_tensor(img_path):
    img=image2.load_img(img_path,target_size=(224,224,3))
    x=image2.img_to_array(img)
    return np.expand_dims(x,axis=0)
def paths_to_tensor(img_paths):
    list_of_tensors=[path_to_tensor(img_path) for img_path in tqdm(img_paths)]
    return np.vstack(list_of_tensors)
def draw_predicted_figure(img_path,x,y):
    fig,ax=plt.subplots()
    fig.set_size_inches(5,5)
    fig_title="\n".join(["{}: {:.2f}%\n".format(n,y[i]) for i,n in enumerate(x)])
    ax.test(1.01,0.7,
            fig_title,
            horizontalalignment='left',
            verticalalignment='bottom',
            transform=ax.transAxes)
    img=image.imread(img_path)
    ax.imshow(img)

if __name__ == '__main__':
    work_path=os.getcwd()
    datasets_path=os.path.join(work_path,'datasets','dataset','dataset')
    data=get_data(datasets_path)
    filename_list=data['filenames']
    target_list=data['target']
    target_name_list=data['target_names']
    print(filename_list.shape)
    print(filename_list[:20])
    print(target_list)
    print(target_name_list)
    plot_image(filename_list)
    '''
    基于Keras的卷积神经网络实现分类
    '''
    x_train,x_test,y_train,y_test=train_test_split(filename_list,target_list,test_size=0.2)
    half_test_count=int(len(x_test)/2)
    x_valid=x_test[:half_test_count]
    y_valid=y_test[:half_test_count]
    x_test=x_test[half_test_count:]
    y_test=y_test[half_test_count:]
    print("X_train.shape={},y_train.shape={}.".format(x_train.shape,y_train.shape))
    print("X_valid.shape={},y_valid.shape={}.".format(x_valid.shape, y_valid.shape))
    print("X_test.shape={},y_test.shape={}.".format(x_test.shape, y_test.shape))
    ImageFile.LOAD_TRUNCATED_IMAGES=True
    train_tensors=paths_to_tensor(x_train).astype(np.float32)/255
    valid_tensors=paths_to_tensor(x_valid).astype(np.float32)/255
    test_tensors = paths_to_tensor(x_test).astype(np.float32) / 255
    '''创建CNN模型'''
    from keras.layers import Conv2D,MaxPooling2D,GlobalAveragePooling2D
    from keras.layers import Dropout,Dense
    from keras.models import Sequential
    from keras.callbacks import ModelCheckpoint
    input_shape=train_tensors[0].shape
    num_classes=len(target_name_list)
    model=Sequential()
    model.add(Conv2D(filters=16,kernel_size=(1,1),strides=(1,1),padding='same',activation='relu',input_shape=input_shape))
    model.add(MaxPooling2D(pool_size=(1,1)))
    model.add(Dropout(0.5))
    model.add(Conv2D(filters=32,kernel_size=(1,1),strides=(1,1),padding='same',activation='relu'))
    model.add(MaxPooling2D(pool_size=(1,1)))
    model.add(Dropout(0.2))
    model.add(GlobalAveragePooling2D())
    model.add(Dropout(0.5))
    model.add(Dense(num_classes,activation='softmax'))
    model.summary()
    model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])
    checkpointer=ModelCheckpoint(filepath='saved_model/skin_cancer.best_weighs.hdf5')
    epochs=10
    model.fit(train_tensors,
              y_train,
              validation_data=(valid_tensors,y_valid),
              epochs=epochs,
              batch_size=20,
              callbacks=[checkpointer],
              verbose=1)
    model.load_weights("saved_model/skin_cancer.best_weighs.hdf5")
    score=model.evaluate(test_tensors,y_test,verbose=1)
    print("Test {}:{:.2f}.Test {}: {:.2f}.".format(model.metrics_names[0],score[0]*100,model.metrics_names[1],score[1]*100))

    from keras.models import load_model
    model=load_model("saved_model/skin_cancer.best_weighs.hdf5")
    test_img_path="nevus_ISIC_0007332.jpg"
    image_tensor=path_to_tensor(test_img_path)
    image_tensor=image_tensor.astype(np.float32)/255
    predicted_result=model.predict(image_tensor)
    print(predicted_result)
    draw_predicted_figure(test_img_path,target_name_list,predicted_result[0])