CNN|ResNet-50

导入数据 import matplotlib.pyplot as plt # 支持中文 plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签 plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 import os,PIL,pathlib import numpy as np from tensorflow import keras from tensorflow.keras import layers,models data_dir = "/Users/yueyishen/jupter/data/bird_photos" data_dir = pathlib.Path(data_dir) 查看数据 image_count = len(list(data_dir.glob('*/*'))) print("图片总数为：",image_count) 图片总数为： 565 数据预处理 1. 加载数据

使用image_dataset_from_directory方法将磁盘中的数据加载到tf.data.Dataset中

batch_size = 8 img_height = 224 img_width = 224 """ 关于image_dataset_from_directory()的详细介绍可以参考文章： mtyjkh.blog.csdn.net/article/details/117018789 """ train_ds = tf.keras.preprocessing.image_dataset_from_directory( data_dir, validation_split=0.2, subset="training", seed=123, image_size=(img_height, img_width), batch_size=batch_size)

Found 565 files belonging to 4 classes. Using 452 files for training. 

""" 关于image_dataset_from_directory()的详细介绍可以参考文章： mtyjkh.blog.csdn.net/article/details/117018789 """ val_ds = tf.keras.preprocessing.image_dataset_from_directory( data_dir, validation_split=0.2, subset="validation", seed=123, image_size=(img_height, img_width), batch_size=batch_size)

Found 565 files belonging to 4 classes. Using 113 files for validation.

class_names = train_ds.class_names print(class_names)

['Bananaquit', 'Black Skimmer', 'Black Throated Bushtiti', 'Cockatoo']

可视化数据 plt.figure(figsize=(10, 5)) # 图形的宽为10高为5 plt.suptitle("瓜牛") for images, labels in train_ds.take(1): for i in range(8): ax = plt.subplot(2, 4, i + 1) plt.imshow(images[i].numpy().astype("uint8")) plt.title(class_names[labels[i]]) plt.axis("off")

再次检查数据 for image_batch, labels_batch in train_ds: print(image_batch.shape) print(labels_batch.shape) break

(8, 224, 224, 3) (8,)

配置数据集

● shuffle() ： 打乱数据

● prefetch() ：预取数据，加速运行，其详细介绍可以参考我前两篇文章，里面都有讲解。

● cache() ：将数据集缓存到内存当中，加速运行

AUTOTUNE = tf.data.AUTOTUNE train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE) val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

构建ResNet-50网络模型

from keras import layers from keras.layers import Input,Activation,BatchNormalization,Flatten from keras.layers import Dense,Conv2D,MaxPooling2D,ZeroPadding2D,AveragePooling2D from keras.models import Model def identity_block(input_tensor, kernel_size, filters, stage, block): filters1, filters2, filters3 = filters name_base = str(stage) + block + '_identity_block_' x = Conv2D(filters1, (1, 1), name=name_base + 'conv1')(input_tensor) x = BatchNormalization(name=name_base + 'bn1')(x) x = Activation('relu', name=name_base + 'relu1')(x) x = Conv2D(filters2, kernel_size,padding='same', name=name_base + 'conv2')(x) x = BatchNormalization(name=name_base + 'bn2')(x) x = Activation('relu', name=name_base + 'relu2')(x) x = Conv2D(filters3, (1, 1), name=name_base + 'conv3')(x) x = BatchNormalization(name=name_base + 'bn3')(x) x = layers.add([x, input_tensor] ,name=name_base + 'add') x = Activation('relu', name=name_base + 'relu4')(x) return x # 在残差网络中，广泛地使用了BN层；但是没有使用MaxPooling以便减小特征图尺寸， # 作为替代，在每个模块的第一层，都使用了strides = (2, 2)的方式进行特征图尺寸缩减， # 与使用MaxPooling相比，毫无疑问是减少了卷积的次数，输入图像分辨率较大时比较适合 # 在残差网络的最后一级，先利用layer.add()实现H(x) = x + F(x) def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)): filters1, filters2, filters3 = filters res_name_base = str(stage) + block + '_conv_block_res_' name_base = str(stage) + block + '_conv_block_' x = Conv2D(filters1, (1, 1), strides=strides, name=name_base + 'conv1')(input_tensor) x = BatchNormalization(name=name_base + 'bn1')(x) x = Activation('relu', name=name_base + 'relu1')(x) x = Conv2D(filters2, kernel_size, padding='same', name=name_base + 'conv2')(x) x = BatchNormalization(name=name_base + 'bn2')(x) x = Activation('relu', name=name_base + 'relu2')(x) x = Conv2D(filters3, (1, 1), name=name_base + 'conv3')(x) x = BatchNormalization(name=name_base + 'bn3')(x) shortcut = Conv2D(filters3, (1, 1), strides=strides, name=res_name_base + 'conv')(input_tensor) shortcut = BatchNormalization(name=res_name_base + 'bn')(shortcut) x = layers.add([x, shortcut], name=name_base+'add') x = Activation('relu', name=name_base+'relu4')(x) return x def ResNet50(input_shape=[224,224,3],classes=1000): img_input = Input(shape=input_shape) x = ZeroPadding2D((3, 3))(img_input) x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x) x = BatchNormalization(name='bn_conv1')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') x = identity_block(x, 3, [128, 128, 512], stage=3, block='b') x = identity_block(x, 3, [128, 128, 512], stage=3, block='c') x = identity_block(x, 3, [128, 128, 512], stage=3, block='d') x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f') x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c') x = AveragePooling2D((7, 7), name='avg_pool')(x) x = Flatten()(x) x = Dense(classes, activation='softmax', name='fc1000')(x) model = Model(img_input, x, name='resnet50') # 加载预训练模型 model.load_weights("/Users/yueyishen/jupter/data/resnet50_weights_tf_dim_ordering_tf_kernels.h5") return model model = ResNet50() model.summary()

编译

在准备对模型进行训练之前，还需要再对其进行一些设置。以下内容是在模型的编译步骤中添加的：

● 损失函数（loss）：用于衡量模型在训练期间的准确率。

● 优化器（optimizer）：决定模型如何根据其看到的数据和自身的损失函数进行更新。

● 指标（metrics）：用于监控训练和测试步骤。以下示例使用了准确率，即被正确分类的图像的比率

model pile(optimizer="adam", loss='sparse_categorical_crossentropy', metrics=['accuracy'])

训练模型 epochs = 10 history = model.fit( train_ds, validation_data=val_ds, epochs=epochs )

 模型评估 acc = history.history['accuracy'] val_acc = history.history['val_accuracy'] loss = history.history['loss'] val_loss = history.history['val_loss'] epochs_range = range(epochs) plt.figure(figsize=(12, 4)) plt.subplot(1, 2, 1) plt.suptitle("微信公众号：K同学啊") plt.plot(epochs_range, acc, label='Training Accuracy') plt.plot(epochs_range, val_acc, label='Validation Accuracy') plt.legend(loc='lower right') plt.title('Training and Validation Accuracy') plt.subplot(1, 2, 2) plt.plot(epochs_range, loss, label='Training Loss') plt.plot(epochs_range, val_loss, label='Validation Loss') plt.legend(loc='upper right') plt.title('Training and Validation Loss') plt.show()

 预测 # 采用加载的模型（new_model）来看预测结果 plt.figure(figsize=(10, 5)) # 图形的宽为10高为5 plt.suptitle("微信公众号：K同学啊") for images, labels in val_ds.take(1): for i in range(8): ax = plt.subplot(2, 4, i + 1) # 显示图片 plt.imshow(images[i].numpy().astype("uint8")) # 需要给图片增加一个维度 img_array = tf.expand_dims(images[i], 0) # 使用模型预测图片中的人物 predictions = model.predict(img_array) plt.title(class_names[np.argmax(predictions)]) plt.axis("off")

 

总结： 数据导入与预处理：首先导入必要的库，设置数据目录，查看数据总数为 565 张图片。使用 image_dataset_from_directory 方法将磁盘中的数据加载为训练集和验证集，进行数据预处理，包括设置图像大小、批次大小等，并对数据集进行打乱、预取和缓存等操作。可视化数据：通过 plt.figure 和循环展示了训练集中的部分图片，并标注了图片的类别名称。再次检查数据，打印出图像批次的形状和标签批次的形状。构建 ResNet-50 网络模型：定义了 identity_block 和 conv_block 函数，用于构建 ResNet-50 模型。该模型接收输入形状为 [224,224,3] 的图像，经过一系列卷积、批归一化、激活和残差连接等操作，最后输出分类结果。编译模型：在编译模型时，设置损失函数为 sparse_categorical_crossentropy，优化器为 adam，指标为准确率。训练模型：使用训练集和验证集对模型进行训练，设置训练轮数为 10 轮。模型评估：绘制训练和验证的准确率及损失曲线，以评估模型的性能。预测：对验证集中的部分图片进行预测，展示预测结果的类别名称