一 数据准备
1.导入数据
import matplotlib.pyplot as plt
import tensorflow as tf
import warnings as w
w.filterwarnings('ignore')
# 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
#隐藏警告
import warnings
warnings.filterwarnings('ignore')
data_dir = "./data"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：",image_count)图片总数为： 5192
2.数据预处理
batch_size = 64
img_height = 224
img_width = 224train_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.3,
subset="training",
seed=12,
image_size=(img_height, img_width),
batch_size=batch_size)Found 5192 files belonging to 2 classes. Using 3635 files for training.
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.3,
subset="validation",
seed=12,
image_size=(img_height, img_width),
batch_size=batch_size)Found 5192 files belonging to 2 classes. Using 1557 files for validation.
class_names = train_ds.class_names
print(class_names)['Normal', 'OSCC']
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break(64, 224, 224, 3) (64,)
AUTOTUNE = tf.data.AUTOTUNE
def preprocess_image(image,label):
return (image/255.0,label)
# 归一化处理
train_ds = train_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
val_ds = val_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)3.可视化数据
plt.figure(figsize=(15, 10)) # 图形的宽为15高为10
for images, labels in train_ds.take(1):
for i in range(15):
ax = plt.subplot(3, 5, i + 1)
plt.imshow(images[i])
plt.title(class_names[labels[i]])
plt.axis("off")
二 ResNet50模型的构建
from keras import layers
from keras.layers import Input,Activation,BatchNormalization,Flatten, Dropout
from keras.layers import Dense,Conv2D,MaxPooling2D,ZeroPadding2D,AveragePooling2D
from keras.models import Model
import tensorflow as tf
def identity_block(input_tensor,kernel_size,filters,stage,block):
'''
:param input_tensor: 输入张量，通常是前一层的输出
:param kernel_size: 卷积核大小，用于第二个卷积层
:param filters: 一个包含三个整数的元组，分别表示三个卷积层的过滤器数量
:param stage: 当前块的阶段，用于命名
:param block: 当前块的名称，用于命名
:return:
'''
# 提取过滤器数量
filters1,filters2,filters3 = filters
# 基础名称生成
name_base = str(stage) + block +'_identity_block_'
# 第一个卷积层，使用1x1卷积对输入进行处理，减少通道数。卷积层之后跟着批归一化和ReLU激活
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)
# 第二个卷积层，使用给定的kernel_size进行卷积，保持输入和输出的空间尺寸相同（通过padding='same'）。同样后续跟着批归一化和ReLU激活
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)
# 第三个卷积层，再次使用1x1卷积来调整输出通道数，随后进行批归一化
x = Conv2D(filters3, (1, 1), name=name_base + 'conv3')(x)
x = BatchNormalization(name=name_base + 'bn3')(x)
# 残差连接，将输入张量和经过卷积层处理后的输出张量相加。这种残差连接有助于缓解梯度消失问题，促进信息流动
x = layers.add([x,input_tensor],name=name_base+'add')
# 加和后的结果上应用ReLU激活函数
x = Activation('relu',name=name_base+'relu4')(x)
return x
'''
在残差网络中，广泛的使用了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)):
'''
input_tensor: 输入张量，通常是前一层的输出。
kernel_size: 卷积核的大小，用于第二个卷积层。
filters: 一个包含三个整数的元组，分别表示三个卷积层的过滤器数量。
stage: 当前块的阶段，通常用于命名。
block: 当前块的名称，用于命名。
strides: 卷积的步幅，默认值为(2, 2)，用于下采样。
'''
# 提取过滤器数量
filters1, filters2, filters3 = filters
# 基础名称生成
res_name_base = str(stage) + block +'_conv_block_res_'
name_base = str(stage) + block +'_conv_block_'
# 使用1x1卷积对输入进行处理，减少通道数。strides参数用于控制下采样，默认步幅为(2, 2)，这将使输出特征图的尺寸减半。后续跟着批归一化和ReLU激活
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)
# 使用给定的kernel_size进行卷积，保持输入和输出的空间尺寸相同（通过padding='same'）。后续同样进行批归一化和ReLU激活
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)
# 使用1x1卷积来调整输出通道数，随后进行批归一化
x = Conv2D(filters3, (1, 1), name=name_base + 'conv3')(x)
x = BatchNormalization(name=name_base + 'bn3')(x)
# 对输入张量进行卷积处理，以匹配输出张量的维度，确保在加法操作时两者具有相同的形状。此卷积层的步幅与主卷积块相同，确保特征图的尺寸一致。随后进行批归一化
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
'''
定义一个ResNet50模型:
输入层：接收形状为 224x224x3 的图像。
零填充：对输入进行 3 像素的零填充，以保持特征图的边界。
初始卷积：使用 64 个 7x7 的卷积核，步幅为 2，之后进行批归一化和 ReLU 激活。
最大池化：进行 3x3 的最大池化，步幅为 2，减少特征图尺寸。
残差块：通过堆叠卷积块（conv_block）和身份块（identity_block）实现特征提取，逐步增加通道数，从 64 到 2048。
平均池化：在最后应用 7x7 的平均池化，降低特征维度。
展平和全连接层：展平特征图，接入一个具有 softmax 激活的全连接层，用于多类分类（2 类）。
加载预训练权重：从指定文件加载预训练的模型权重，便于迁移学习。
该架构旨在有效捕捉图像特征，适合深度学习任务
'''
def ResNet50(input_shape=[224,224,3],classes=2):
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)
# 在全连接层之前添加 Dropout 层
x = Dropout(0.5)(x) # 这里设置 Dropout 比率为 50%
x = Dense(classes,activation='softmax',name='fc2')(x)
model = Model(img_input,x,name='resnet50')
# 加载预训练模型
# model.load_weights("resnet50_weights_tf_dim_ordering_tf_kernels.h5")
return model
model = ResNet50()
model.summary()Model: "resnet50"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_2 (InputLayer) [(None, 224, 224, 3 0 []
)]
zero_padding2d_1 (ZeroPadding2 (None, 230, 230, 3) 0 ['input_2[0][0]']
D)
conv1 (Conv2D) (None, 112, 112, 64 9472 ['zero_padding2d_1[0][0]']
)
bn_conv1 (BatchNormalization) (None, 112, 112, 64 256 ['conv1[0][0]']
)
activation_1 (Activation) (None, 112, 112, 64 0 ['bn_conv1[0][0]']
)
max_pooling2d_1 (MaxPooling2D) (None, 55, 55, 64) 0 ['activation_1[0][0]']
2a_conv_block_conv1 (Conv2D) (None, 55, 55, 64) 4160 ['max_pooling2d_1[0][0]']
2a_conv_block_bn1 (BatchNormal (None, 55, 55, 64) 256 ['2a_conv_block_conv1[0][0]']
ization)
2a_conv_block_relu1 (Activatio (None, 55, 55, 64) 0 ['2a_conv_block_bn1[0][0]']
n)
2a_conv_block_conv2 (Conv2D) (None, 55, 55, 64) 36928 ['2a_conv_block_relu1[0][0]']
2a_conv_block_bn2 (BatchNormal (None, 55, 55, 64) 256 ['2a_conv_block_conv2[0][0]']
ization)
2a_conv_block_relu2 (Activatio (None, 55, 55, 64) 0 ['2a_conv_block_bn2[0][0]']
n)
2a_conv_block_conv3 (Conv2D) (None, 55, 55, 256) 16640 ['2a_conv_block_relu2[0][0]']
2a_conv_block_res_conv (Conv2D (None, 55, 55, 256) 16640 ['max_pooling2d_1[0][0]']
)
2a_conv_block_bn3 (BatchNormal (None, 55, 55, 256) 1024 ['2a_conv_block_conv3[0][0]']
ization)
2a_conv_block_res_bn (BatchNor (None, 55, 55, 256) 1024 ['2a_conv_block_res_conv[0][0]']
malization)
2a_conv_block_add (Add) (None, 55, 55, 256) 0 ['2a_conv_block_bn3[0][0]',
'2a_conv_block_res_bn[0][0]']
2a_conv_block_relu4 (Activatio (None, 55, 55, 256) 0 ['2a_conv_block_add[0][0]']
n)
2b_identity_block_conv1 (Conv2 (None, 55, 55, 64) 16448 ['2a_conv_block_relu4[0][0]']
D)
2b_identity_block_bn1 (BatchNo (None, 55, 55, 64) 256 ['2b_identity_block_conv1[0][0]']
rmalization)
2b_identity_block_relu1 (Activ (None, 55, 55, 64) 0 ['2b_identity_block_bn1[0][0]']
ation)
2b_identity_block_conv2 (Conv2 (None, 55, 55, 64) 36928 ['2b_identity_block_relu1[0][0]']
D)
2b_identity_block_bn2 (BatchNo (None, 55, 55, 64) 256 ['2b_identity_block_conv2[0][0]']
rmalization)
2b_identity_block_relu2 (Activ (None, 55, 55, 64) 0 ['2b_identity_block_bn2[0][0]']
ation)
2b_identity_block_conv3 (Conv2 (None, 55, 55, 256) 16640 ['2b_identity_block_relu2[0][0]']
D)
2b_identity_block_bn3 (BatchNo (None, 55, 55, 256) 1024 ['2b_identity_block_conv3[0][0]']
rmalization)
2b_identity_block_add (Add) (None, 55, 55, 256) 0 ['2b_identity_block_bn3[0][0]',
'2a_conv_block_relu4[0][0]']
2b_identity_block_relu4 (Activ (None, 55, 55, 256) 0 ['2b_identity_block_add[0][0]']
ation)
2c_identity_block_conv1 (Conv2 (None, 55, 55, 64) 16448 ['2b_identity_block_relu4[0][0]']
D)
2c_identity_block_bn1 (BatchNo (None, 55, 55, 64) 256 ['2c_identity_block_conv1[0][0]']
rmalization)
2c_identity_block_relu1 (Activ (None, 55, 55, 64) 0 ['2c_identity_block_bn1[0][0]']
ation)
2c_identity_block_conv2 (Conv2 (None, 55, 55, 64) 36928 ['2c_identity_block_relu1[0][0]']
D)
2c_identity_block_bn2 (BatchNo (None, 55, 55, 64) 256 ['2c_identity_block_conv2[0][0]']
rmalization)
2c_identity_block_relu2 (Activ (None, 55, 55, 64) 0 ['2c_identity_block_bn2[0][0]']
ation)
2c_identity_block_conv3 (Conv2 (None, 55, 55, 256) 16640 ['2c_identity_block_relu2[0][0]']
D)
2c_identity_block_bn3 (BatchNo (None, 55, 55, 256) 1024 ['2c_identity_block_conv3[0][0]']
rmalization)
2c_identity_block_add (Add) (None, 55, 55, 256) 0 ['2c_identity_block_bn3[0][0]',
'2b_identity_block_relu4[0][0]']
2c_identity_block_relu4 (Activ (None, 55, 55, 256) 0 ['2c_identity_block_add[0][0]']
ation)
3a_conv_block_conv1 (Conv2D) (None, 28, 28, 128) 32896 ['2c_identity_block_relu4[0][0]']
3a_conv_block_bn1 (BatchNormal (None, 28, 28, 128) 512 ['3a_conv_block_conv1[0][0]']
ization)
3a_conv_block_relu1 (Activatio (None, 28, 28, 128) 0 ['3a_conv_block_bn1[0][0]']
n)
3a_conv_block_conv2 (Conv2D) (None, 28, 28, 128) 147584 ['3a_conv_block_relu1[0][0]']
3a_conv_block_bn2 (BatchNormal (None, 28, 28, 128) 512 ['3a_conv_block_conv2[0][0]']
ization)
3a_conv_block_relu2 (Activatio (None, 28, 28, 128) 0 ['3a_conv_block_bn2[0][0]']
n)
3a_conv_block_conv3 (Conv2D) (None, 28, 28, 512) 66048 ['3a_conv_block_relu2[0][0]']
3a_conv_block_res_conv (Conv2D (None, 28, 28, 512) 131584 ['2c_identity_block_relu4[0][0]']
)
3a_conv_block_bn3 (BatchNormal (None, 28, 28, 512) 2048 ['3a_conv_block_conv3[0][0]']
ization)
3a_conv_block_res_bn (BatchNor (None, 28, 28, 512) 2048 ['3a_conv_block_res_conv[0][0]']
malization)
3a_conv_block_add (Add) (None, 28, 28, 512) 0 ['3a_conv_block_bn3[0][0]',
'3a_conv_block_res_bn[0][0]']
3a_conv_block_relu4 (Activatio (None, 28, 28, 512) 0 ['3a_conv_block_add[0][0]']
n)
3b_identity_block_conv1 (Conv2 (None, 28, 28, 128) 65664 ['3a_conv_block_relu4[0][0]']
D)
3b_identity_block_bn1 (BatchNo (None, 28, 28, 128) 512 ['3b_identity_block_conv1[0][0]']
rmalization)
3b_identity_block_relu1 (Activ (None, 28, 28, 128) 0 ['3b_identity_block_bn1[0][0]']
ation)
3b_identity_block_conv2 (Conv2 (None, 28, 28, 128) 147584 ['3b_identity_block_relu1[0][0]']
D)
3b_identity_block_bn2 (BatchNo (None, 28, 28, 128) 512 ['3b_identity_block_conv2[0][0]']
rmalization)
3b_identity_block_relu2 (Activ (None, 28, 28, 128) 0 ['3b_identity_block_bn2[0][0]']
ation)
3b_identity_block_conv3 (Conv2 (None, 28, 28, 512) 66048 ['3b_identity_block_relu2[0][0]']
D)
3b_identity_block_bn3 (BatchNo (None, 28, 28, 512) 2048 ['3b_identity_block_conv3[0][0]']
rmalization)
3b_identity_block_add (Add) (None, 28, 28, 512) 0 ['3b_identity_block_bn3[0][0]',
'3a_conv_block_relu4[0][0]']
3b_identity_block_relu4 (Activ (None, 28, 28, 512) 0 ['3b_identity_block_add[0][0]']
ation)
3c_identity_block_conv1 (Conv2 (None, 28, 28, 128) 65664 ['3b_identity_block_relu4[0][0]']
D)
3c_identity_block_bn1 (BatchNo (None, 28, 28, 128) 512 ['3c_identity_block_conv1[0][0]']
rmalization)
3c_identity_block_relu1 (Activ (None, 28, 28, 128) 0 ['3c_identity_block_bn1[0][0]']
ation)
3c_identity_block_conv2 (Conv2 (None, 28, 28, 128) 147584 ['3c_identity_block_relu1[0][0]']
D)
3c_identity_block_bn2 (BatchNo (None, 28, 28, 128) 512 ['3c_identity_block_conv2[0][0]']
rmalization)
3c_identity_block_relu2 (Activ (None, 28, 28, 128) 0 ['3c_identity_block_bn2[0][0]']
ation)
3c_identity_block_conv3 (Conv2 (None, 28, 28, 512) 66048 ['3c_identity_block_relu2[0][0]']
D)
3c_identity_block_bn3 (BatchNo (None, 28, 28, 512) 2048 ['3c_identity_block_conv3[0][0]']
rmalization)
3c_identity_block_add (Add) (None, 28, 28, 512) 0 ['3c_identity_block_bn3[0][0]',
'3b_identity_block_relu4[0][0]']
3c_identity_block_relu4 (Activ (None, 28, 28, 512) 0 ['3c_identity_block_add[0][0]']
ation)
3d_identity_block_conv1 (Conv2 (None, 28, 28, 128) 65664 ['3c_identity_block_relu4[0][0]']
D)
3d_identity_block_bn1 (BatchNo (None, 28, 28, 128) 512 ['3d_identity_block_conv1[0][0]']
rmalization)
3d_identity_block_relu1 (Activ (None, 28, 28, 128) 0 ['3d_identity_block_bn1[0][0]']
ation)
3d_identity_block_conv2 (Conv2 (None, 28, 28, 128) 147584 ['3d_identity_block_relu1[0][0]']
D)
3d_identity_block_bn2 (BatchNo (None, 28, 28, 128) 512 ['3d_identity_block_conv2[0][0]']
rmalization)
3d_identity_block_relu2 (Activ (None, 28, 28, 128) 0 ['3d_identity_block_bn2[0][0]']
ation)
3d_identity_block_conv3 (Conv2 (None, 28, 28, 512) 66048 ['3d_identity_block_relu2[0][0]']
D)
3d_identity_block_bn3 (BatchNo (None, 28, 28, 512) 2048 ['3d_identity_block_conv3[0][0]']
rmalization)
3d_identity_block_add (Add) (None, 28, 28, 512) 0 ['3d_identity_block_bn3[0][0]',
'3c_identity_block_relu4[0][0]']
3d_identity_block_relu4 (Activ (None, 28, 28, 512) 0 ['3d_identity_block_add[0][0]']
ation)
4a_conv_block_conv1 (Conv2D) (None, 14, 14, 256) 131328 ['3d_identity_block_relu4[0][0]']
4a_conv_block_bn1 (BatchNormal (None, 14, 14, 256) 1024 ['4a_conv_block_conv1[0][0]']
ization)
4a_conv_block_relu1 (Activatio (None, 14, 14, 256) 0 ['4a_conv_block_bn1[0][0]']
n)
4a_conv_block_conv2 (Conv2D) (None, 14, 14, 256) 590080 ['4a_conv_block_relu1[0][0]']
4a_conv_block_bn2 (BatchNormal (None, 14, 14, 256) 1024 ['4a_conv_block_conv2[0][0]']
ization)
4a_conv_block_relu2 (Activatio (None, 14, 14, 256) 0 ['4a_conv_block_bn2[0][0]']
n)
4a_conv_block_conv3 (Conv2D) (None, 14, 14, 1024 263168 ['4a_conv_block_relu2[0][0]']
)
4a_conv_block_res_conv (Conv2D (None, 14, 14, 1024 525312 ['3d_identity_block_relu4[0][0]']
) )
4a_conv_block_bn3 (BatchNormal (None, 14, 14, 1024 4096 ['4a_conv_block_conv3[0][0]']
ization) )
4a_conv_block_res_bn (BatchNor (None, 14, 14, 1024 4096 ['4a_conv_block_res_conv[0][0]']
malization) )
4a_conv_block_add (Add) (None, 14, 14, 1024 0 ['4a_conv_block_bn3[0][0]',
) '4a_conv_block_res_bn[0][0]']
4a_conv_block_relu4 (Activatio (None, 14, 14, 1024 0 ['4a_conv_block_add[0][0]']
n) )
4b_identity_block_conv1 (Conv2 (None, 14, 14, 256) 262400 ['4a_conv_block_relu4[0][0]']
D)
4b_identity_block_bn1 (BatchNo (None, 14, 14, 256) 1024 ['4b_identity_block_conv1[0][0]']
rmalization)
4b_identity_block_relu1 (Activ (None, 14, 14, 256) 0 ['4b_identity_block_bn1[0][0]']
ation)
4b_identity_block_conv2 (Conv2 (None, 14, 14, 256) 590080 ['4b_identity_block_relu1[0][0]']
D)
4b_identity_block_bn2 (BatchNo (None, 14, 14, 256) 1024 ['4b_identity_block_conv2[0][0]']
rmalization)
4b_identity_block_relu2 (Activ (None, 14, 14, 256) 0 ['4b_identity_block_bn2[0][0]']
ation)
4b_identity_block_conv3 (Conv2 (None, 14, 14, 1024 263168 ['4b_identity_block_relu2[0][0]']
D) )
4b_identity_block_bn3 (BatchNo (None, 14, 14, 1024 4096 ['4b_identity_block_conv3[0][0]']
rmalization) )
4b_identity_block_add (Add) (None, 14, 14, 1024 0 ['4b_identity_block_bn3[0][0]',
) '4a_conv_block_relu4[0][0]']
4b_identity_block_relu4 (Activ (None, 14, 14, 1024 0 ['4b_identity_block_add[0][0]']
ation) )
4c_identity_block_conv1 (Conv2 (None, 14, 14, 256) 262400 ['4b_identity_block_relu4[0][0]']
D)
4c_identity_block_bn1 (BatchNo (None, 14, 14, 256) 1024 ['4c_identity_block_conv1[0][0]']
rmalization)
4c_identity_block_relu1 (Activ (None, 14, 14, 256) 0 ['4c_identity_block_bn1[0][0]']
ation)
4c_identity_block_conv2 (Conv2 (None, 14, 14, 256) 590080 ['4c_identity_block_relu1[0][0]']
D)
4c_identity_block_bn2 (BatchNo (None, 14, 14, 256) 1024 ['4c_identity_block_conv2[0][0]']
rmalization)
4c_identity_block_relu2 (Activ (None, 14, 14, 256) 0 ['4c_identity_block_bn2[0][0]']
ation)
4c_identity_block_conv3 (Conv2 (None, 14, 14, 1024 263168 ['4c_identity_block_relu2[0][0]']
D) )
4c_identity_block_bn3 (BatchNo (None, 14, 14, 1024 4096 ['4c_identity_block_conv3[0][0]']
rmalization) )
4c_identity_block_add (Add) (None, 14, 14, 1024 0 ['4c_identity_block_bn3[0][0]',
) '4b_identity_block_relu4[0][0]']
4c_identity_block_relu4 (Activ (None, 14, 14, 1024 0 ['4c_identity_block_add[0][0]']
ation) )
4d_identity_block_conv1 (Conv2 (None, 14, 14, 256) 262400 ['4c_identity_block_relu4[0][0]']
D)
4d_identity_block_bn1 (BatchNo (None, 14, 14, 256) 1024 ['4d_identity_block_conv1[0][0]']
rmalization)
4d_identity_block_relu1 (Activ (None, 14, 14, 256) 0 ['4d_identity_block_bn1[0][0]']
ation)
4d_identity_block_conv2 (Conv2 (None, 14, 14, 256) 590080 ['4d_identity_block_relu1[0][0]']
D)
4d_identity_block_bn2 (BatchNo (None, 14, 14, 256) 1024 ['4d_identity_block_conv2[0][0]']
rmalization)
4d_identity_block_relu2 (Activ (None, 14, 14, 256) 0 ['4d_identity_block_bn2[0][0]']
ation)
4d_identity_block_conv3 (Conv2 (None, 14, 14, 1024 263168 ['4d_identity_block_relu2[0][0]']
D) )
4d_identity_block_bn3 (BatchNo (None, 14, 14, 1024 4096 ['4d_identity_block_conv3[0][0]']
rmalization) )
4d_identity_block_add (Add) (None, 14, 14, 1024 0 ['4d_identity_block_bn3[0][0]',
) '4c_identity_block_relu4[0][0]']
4d_identity_block_relu4 (Activ (None, 14, 14, 1024 0 ['4d_identity_block_add[0][0]']
ation) )
4e_identity_block_conv1 (Conv2 (None, 14, 14, 256) 262400 ['4d_identity_block_relu4[0][0]']
D)
4e_identity_block_bn1 (BatchNo (None, 14, 14, 256) 1024 ['4e_identity_block_conv1[0][0]']
rmalization)
4e_identity_block_relu1 (Activ (None, 14, 14, 256) 0 ['4e_identity_block_bn1[0][0]']
ation)
4e_identity_block_conv2 (Conv2 (None, 14, 14, 256) 590080 ['4e_identity_block_relu1[0][0]']
D)
4e_identity_block_bn2 (BatchNo (None, 14, 14, 256) 1024 ['4e_identity_block_conv2[0][0]']
rmalization)
4e_identity_block_relu2 (Activ (None, 14, 14, 256) 0 ['4e_identity_block_bn2[0][0]']
ation)
4e_identity_block_conv3 (Conv2 (None, 14, 14, 1024 263168 ['4e_identity_block_relu2[0][0]']
D) )
4e_identity_block_bn3 (BatchNo (None, 14, 14, 1024 4096 ['4e_identity_block_conv3[0][0]']
rmalization) )
4e_identity_block_add (Add) (None, 14, 14, 1024 0 ['4e_identity_block_bn3[0][0]',
) '4d_identity_block_relu4[0][0]']
4e_identity_block_relu4 (Activ (None, 14, 14, 1024 0 ['4e_identity_block_add[0][0]']
ation) )
4f_identity_block_conv1 (Conv2 (None, 14, 14, 256) 262400 ['4e_identity_block_relu4[0][0]']
D)
4f_identity_block_bn1 (BatchNo (None, 14, 14, 256) 1024 ['4f_identity_block_conv1[0][0]']
rmalization)
4f_identity_block_relu1 (Activ (None, 14, 14, 256) 0 ['4f_identity_block_bn1[0][0]']
ation)
4f_identity_block_conv2 (Conv2 (None, 14, 14, 256) 590080 ['4f_identity_block_relu1[0][0]']
D)
4f_identity_block_bn2 (BatchNo (None, 14, 14, 256) 1024 ['4f_identity_block_conv2[0][0]']
rmalization)
4f_identity_block_relu2 (Activ (None, 14, 14, 256) 0 ['4f_identity_block_bn2[0][0]']
ation)
4f_identity_block_conv3 (Conv2 (None, 14, 14, 1024 263168 ['4f_identity_block_relu2[0][0]']
D) )
4f_identity_block_bn3 (BatchNo (None, 14, 14, 1024 4096 ['4f_identity_block_conv3[0][0]']
rmalization) )
4f_identity_block_add (Add) (None, 14, 14, 1024 0 ['4f_identity_block_bn3[0][0]',
) '4e_identity_block_relu4[0][0]']
4f_identity_block_relu4 (Activ (None, 14, 14, 1024 0 ['4f_identity_block_add[0][0]']
ation) )
5a_conv_block_conv1 (Conv2D) (None, 7, 7, 512) 524800 ['4f_identity_block_relu4[0][0]']
5a_conv_block_bn1 (BatchNormal (None, 7, 7, 512) 2048 ['5a_conv_block_conv1[0][0]']
ization)
5a_conv_block_relu1 (Activatio (None, 7, 7, 512) 0 ['5a_conv_block_bn1[0][0]']
n)
5a_conv_block_conv2 (Conv2D) (None, 7, 7, 512) 2359808 ['5a_conv_block_relu1[0][0]']
5a_conv_block_bn2 (BatchNormal (None, 7, 7, 512) 2048 ['5a_conv_block_conv2[0][0]']
ization)
5a_conv_block_relu2 (Activatio (None, 7, 7, 512) 0 ['5a_conv_block_bn2[0][0]']
n)
5a_conv_block_conv3 (Conv2D) (None, 7, 7, 2048) 1050624 ['5a_conv_block_relu2[0][0]']
5a_conv_block_res_conv (Conv2D (None, 7, 7, 2048) 2099200 ['4f_identity_block_relu4[0][0]']
)
5a_conv_block_bn3 (BatchNormal (None, 7, 7, 2048) 8192 ['5a_conv_block_conv3[0][0]']
ization)
5a_conv_block_res_bn (BatchNor (None, 7, 7, 2048) 8192 ['5a_conv_block_res_conv[0][0]']
malization)
5a_conv_block_add (Add) (None, 7, 7, 2048) 0 ['5a_conv_block_bn3[0][0]',
'5a_conv_block_res_bn[0][0]']
5a_conv_block_relu4 (Activatio (None, 7, 7, 2048) 0 ['5a_conv_block_add[0][0]']
n)
5b_identity_block_conv1 (Conv2 (None, 7, 7, 512) 1049088 ['5a_conv_block_relu4[0][0]']
D)
5b_identity_block_bn1 (BatchNo (None, 7, 7, 512) 2048 ['5b_identity_block_conv1[0][0]']
rmalization)
5b_identity_block_relu1 (Activ (None, 7, 7, 512) 0 ['5b_identity_block_bn1[0][0]']
ation)
5b_identity_block_conv2 (Conv2 (None, 7, 7, 512) 2359808 ['5b_identity_block_relu1[0][0]']
D)
5b_identity_block_bn2 (BatchNo (None, 7, 7, 512) 2048 ['5b_identity_block_conv2[0][0]']
rmalization)
5b_identity_block_relu2 (Activ (None, 7, 7, 512) 0 ['5b_identity_block_bn2[0][0]']
ation)
5b_identity_block_conv3 (Conv2 (None, 7, 7, 2048) 1050624 ['5b_identity_block_relu2[0][0]']
D)
5b_identity_block_bn3 (BatchNo (None, 7, 7, 2048) 8192 ['5b_identity_block_conv3[0][0]']
rmalization)
5b_identity_block_add (Add) (None, 7, 7, 2048) 0 ['5b_identity_block_bn3[0][0]',
'5a_conv_block_relu4[0][0]']
5b_identity_block_relu4 (Activ (None, 7, 7, 2048) 0 ['5b_identity_block_add[0][0]']
ation)
5c_identity_block_conv1 (Conv2 (None, 7, 7, 512) 1049088 ['5b_identity_block_relu4[0][0]']
D)
5c_identity_block_bn1 (BatchNo (None, 7, 7, 512) 2048 ['5c_identity_block_conv1[0][0]']
rmalization)
5c_identity_block_relu1 (Activ (None, 7, 7, 512) 0 ['5c_identity_block_bn1[0][0]']
ation)
5c_identity_block_conv2 (Conv2 (None, 7, 7, 512) 2359808 ['5c_identity_block_relu1[0][0]']
D)
5c_identity_block_bn2 (BatchNo (None, 7, 7, 512) 2048 ['5c_identity_block_conv2[0][0]']
rmalization)
5c_identity_block_relu2 (Activ (None, 7, 7, 512) 0 ['5c_identity_block_bn2[0][0]']
ation)
5c_identity_block_conv3 (Conv2 (None, 7, 7, 2048) 1050624 ['5c_identity_block_relu2[0][0]']
D)
5c_identity_block_bn3 (BatchNo (None, 7, 7, 2048) 8192 ['5c_identity_block_conv3[0][0]']
rmalization)
5c_identity_block_add (Add) (None, 7, 7, 2048) 0 ['5c_identity_block_bn3[0][0]',
'5b_identity_block_relu4[0][0]']
5c_identity_block_relu4 (Activ (None, 7, 7, 2048) 0 ['5c_identity_block_add[0][0]']
ation)
avg_pool (AveragePooling2D) (None, 1, 1, 2048) 0 ['5c_identity_block_relu4[0][0]']
flatten_1 (Flatten) (None, 2048) 0 ['avg_pool[0][0]']
dropout (Dropout) (None, 2048) 0 ['flatten_1[0][0]']
fc2 (Dense) (None, 2) 4098 ['dropout[0][0]']
==================================================================================================
Total params: 23,591,810
Trainable params: 23,538,690
Non-trainable params: 53,120
__________________________________________________________________________________________________
三 编译
# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=1e-7)
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])四 训练模型
from keras.callbacks import EarlyStopping
# 设置早停法
early_stopping = EarlyStopping(
monitor='val_loss',
patience=3,
verbose=1,
restore_best_weights=True
)
epochs = 10
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs,
callbacks=[early_stopping]
)Epoch 1/10 57/57 [==============================] - 709s 12s/step - loss: 0.9055 - accuracy: 0.6853 - val_loss: 1.0100 - val_accuracy: 0.4913 Epoch 2/10 57/57 [==============================] - 681s 12s/step - loss: 0.5338 - accuracy: 0.7667 - val_loss: 0.7880 - val_accuracy: 0.4978 Epoch 3/10 57/57 [==============================] - 662s 12s/step - loss: 0.4756 - accuracy: 0.7829 - val_loss: 0.7841 - val_accuracy: 0.4290 Epoch 4/10 57/57 [==============================] - 660s 12s/step - loss: 0.4223 - accuracy: 0.8102 - val_loss: 0.7710 - val_accuracy: 0.5466 Epoch 5/10 57/57 [==============================] - 662s 12s/step - loss: 0.3743 - accuracy: 0.8347 - val_loss: 0.8795 - val_accuracy: 0.5748 Epoch 6/10 57/57 [==============================] - 665s 12s/step - loss: 0.3481 - accuracy: 0.8468 - val_loss: 1.2726 - val_accuracy: 0.4579 Epoch 7/10 57/57 [==============================] - ETA: 0s - loss: 0.3365 - accuracy: 0.8556 Restoring model weights from the end of the best epoch: 4. 57/57 [==============================] - 661s 12s/step - loss: 0.3365 - accuracy: 0.8556 - val_loss: 0.9570 - val_accuracy: 0.5812 Epoch 7: early stopping
五 模型评估
# 获取实际训练轮数
actual_epochs = len(history.history['accuracy'])
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs_range = range(actual_epochs)
plt.figure(figsize=(12, 4))
# 绘制准确率
plt.subplot(1, 2, 1)
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')
# 绘制损失
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()
六 预测
import numpy as np
# 采用加载的模型（new_model）来看预测结果
plt.figure(figsize=(18, 3)) # 图形的宽为18高为5
plt.suptitle("预测结果展示")
for images, labels in val_ds.take(1):
for i in range(8):
ax = plt.subplot(1,8, i + 1)
# 显示图片
plt.imshow(images[i].numpy())
# 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")
1/1 [==============================] - 1s 699ms/step 1/1 [==============================] - 0s 68ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 68ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 78ms/step 1/1 [==============================] - 0s 63ms/step
