医学图像细胞分类.rar

from keras.preprocessing.image import ImageDataGenerator, load_img, img_to_array, array_to_img from keras.models import Sequential from keras.layers import Conv2D, MaxPooling2D from keras.layers import Activation, Dropout, Flatten, Dense from keras import backend as K import numpy as np import matplotlib.pyplot as plt import glob, os, random path = 'Micro_Organism' os.path.join(path, '*/*.*') # 使用 glob 模块批量匹配图像, * 代表匹配所有东西 img_list = glob.glob(os.path.join(path, '*/*.*')) print('>>>图像数量：', len(img_list)) img_list[:5] print(img_list[:5]) # 加载前面几张未感染的图像 for i, img_path in enumerate(img_list[10:16]): img_plot = load_img(img_path) # 加载图像 arr = img_to_array(img_plot) # 将图像转换成数组 print(arr.shape) # 图像形状 plt.subplot(2, 3, i+1) plt.imshow(img_plot) plt.show() # 统一定义图像像素的宽度和高度 img_width, img_height = 100, 100 # 定义训练集、验证集的图形路径（文件夹路径即可） train_data_dir = 'Micro_Organism/' validation_data_dir = 'Micro_Organism/' # 模型训练的参数设置 nb_train_samples = 275 nb_validation_samples = 200 epochs = 20 # 迭代次数 batch_size = 64 # 每个批量观测数 # 图像输入维度设置 if K.image_data_format() == 'channels_first': input_shape = (3, img_width, img_height) else: input_shape = (img_width, img_height, 3) # 统一定义图像像素的宽度和高度 img_width, img_height = 100, 100 # 图像输入维度设置 if K.image_data_format() == 'channels_first': input_shape = (3, img_width, img_height) else: input_shape = (img_width, img_height, 3) train_datagen = ImageDataGenerator(rescale=1. / 255, # 重缩放因子 shear_range=0.2, # 剪切强度（以弧度逆时针方向剪切角度） zoom_range=0.2, # 随机缩放范围 horizontal_flip=True # 随机水平翻转 ) train_generator = train_datagen.flow_from_directory(train_data_dir, # 训练数据的文件夹路径 target_size=(img_width, img_height), # 统一像素大小 batch_size=batch_size, # 每一批次的观测数 class_mode='categorical' # 指定分类模式，指定二分类 ) test_datagen = ImageDataGenerator(rescale=1. / 255, shear_range=0.2, # 剪切强度（以弧度逆时针方向剪切角度） zoom_range=0.2, # 随机缩放范围 horizontal_flip=True)# 随机水平翻转 validation_generator = test_datagen.flow_from_directory(validation_data_dir, # 验证集文件夹路径 target_size=(img_width, img_height), batch_size=batch_size, class_mode='categorical' # 二分类 ) model = Sequential() # ----------------------------------------------------- # 输入层：第一层 # 添加第一个卷积层/最大池化层(必选) model.add(Conv2D(filters=32, # 32 个过滤器 kernel_size=(3, 3), # 卷积核大小 3 x 3 input_shape=input_shape, # 图像输入维度 activation='relu')) # 'relu' 激活函数 model.add(MaxPooling2D(pool_size=(2, 2))) # 池化核大小 2 x 2 # ---------------------------------------------------- # 隐藏层：介于第一层和最后一层之间 # 添加第二个卷积层/最大池化层(可选) model.add(Conv2D(filters=32, kernel_size=(3, 3), activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) # 添加第三个卷积层/最大池化层(可选) model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) # 由于卷积层是 2D 空间，训练时需要将数据展平为 1D 空间 model.add(Flatten()) # 添加展平层(必选) model.add(Dense(units=64, activation='relu')) # 添加全连接层(必选) 64 个神经元 model.add(Dropout(0.5)) # 添加丢弃层，防止过拟合 # --------------------------------------------------- # 输出层：最后一层，神经元控制输出的维度，并指定分类激活函数 类别 model.add(Dense(units=8, activation='sigmoid')) # 指定分类激活函数 print(model.summary()) model.compile(loss='categorical_crossentropy', # 指定损失函数类型 optimizer='rmsprop', # 优化器 metrics=['accuracy']) # 评价指标 history = model.fit_generator(train_generator, steps_per_epoch=nb_train_samples // batch_size, epochs=epochs, validation_data=validation_generator, validation_steps=nb_validation_samples // batch_size ) # 保存整个模型 model.save('model.h5') # 加载模型 from keras.models import load_model from keras.preprocessing import image from keras.applications.vgg16 import preprocess_input import os # 指定要列出子文件和子文件夹的目录路径 folder_path = 'Micro_Organism' # 替换为你要获取子文件和子文件夹的目录路径 # 获取指定路径下的所有文件和文件夹列表 contents = os.listdir(folder_path) print('contents',contents) model = load_model('model.h5') img_path = '测试1.jpg' # img_width, img_height = 100, 100 img = image.load_img(img_path, target_size=(100, 100)) # 例如，针对VGG模型，resize图像为224x224 x = image.img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x) # 预处理图像数据，例如针对VGG模型 # 对测试图像进行预测 predictions = model.predict(x) print(predictions.shape) print('predictions:',predictions) predictions=predictions[0] max_indices = [i for i, value in enumerate(predictions) if value == max(predictions)][0] print(contents[max_indices]) import matplotlib.pyplot as plt training_loss = history.history['loss'] test_loss = history.history['val_loss'] # 创建迭代数量 epoch_count = range(1, len(training_loss) + 1) # 可视化损失历史 plt.plot(epoch_count, training_loss, 'r--') plt.plot(epoch_count, test_loss, 'b-') plt.legend(['Training Loss', 'Test Loss']) plt.xlabel('Epoch') plt.ylabel('Loss') plt.savefig('epochs_loss.png') plt.show() plt.clf() # train_acc = history.history['acc'] train_acc = history.history['accuracy'] test_acc = history.history['val_accuracy'] epoch_counts = range(1, len(train_acc)+1) plt.plot(epoch_counts, train_acc, 'r--', marker='^') plt.plot(epoch_counts, test_acc, linestyle='-', marker='o', color='y') plt.title('accuracy condition') plt.legend(['train_acc', 'test_acc']) plt.xlabel('epochs') plt.ylabel('acc') plt.savefig('epochs_acc.png') plt.show()