秦州区住房和城乡建设局网站郑州网站优化公司
文章目录
- 一、准备工作
- 1.设置GPU
- 2.导入数据
- 3.查看数据
- 二、数据预处理
- 1.加载数据
- 2.可视化数据
- 总结
- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者：K同学啊
一、准备工作
1.设置GPU
import tensorflow as tf gpus = tf.config.list_physical_devices("GPU")if gpus:tf.config.experimental.set_memory_growth(gpus[0], True) # 设置GPUtf.config.set_visible_devices([gpus[0]], "GPU")
2.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 npfrom tensorflow import keras
from tensorflow.keras import layers, models
data_dir = "8/bird_photos"data_dir = pathlib.Path(data_dir)
3.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
二、数据预处理
1.加载数据
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：https://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：https://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’]
2.可视化数据
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 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")
plt.imshow(images[1].numpy().astype("uint8"))
<matplotlib.image.AxesImage at 0x16a64ec80>
3.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,)
2025-02-14 10:51:27.038555: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_4’ with dtype int32 and shape [452]
[[{{node Placeholder/_4}}]]
2025-02-14 10:51:27.039049: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_4’ with dtype int32 and shape [452]
[[{{node Placeholder/_4}}]]
4.配置数据集
AUTOTUNE = tf.data.AUTOTUNEtrain_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
四、模型复现
tf.keras.applications.resnet_v2.ResNet50V2(include_top=True,weights='imagenet',input_tensor=None,input_shape=None,pooling=None,classes=1000,classifier_activation='softmax'
)
<keras.engine.functional.Functional at 0x16ab97a60>
import tensorflow as tf
import tensorflow.keras.layers as layers
from tensorflow.keras.models import Model
1.Residual Block
def block2(x, filters, kernel_size=3, stride=1, conv_shortcut=False, name=None):preact = layers.BatchNormalization(name=name + '_preact_bn')(x)preact = layers.Activation('relu', name=name + '_preact_relu')(preact)if conv_shortcut:shortcut = layers.Conv2D(4 * filters, 1, strides=stride, name=name + '_0_conv')(preact)else:shortcut = layers.MaxPooling2D(1, strides=stride)(x) if stride > 1 else xx = layers.Conv2D(filters, 1, strides=1, use_bias=False, name=name + '_1_conv')(preact)x = layers.BatchNormalization(name=name + '_1_bn')(x)x = layers.Activation('relu', name=name + '_1_relu')(x)x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name=name + '_2_pad')(x)x = layers.Conv2D(filters,kernel_size,strides=stride,use_bias=False,name=name + '_2_conv')(x)x = layers.BatchNormalization(name=name + '_2_bn')(x)x = layers.Activation('relu', name=name + '_2_relu')(x)x = layers.Conv2D(4 * filters, 1, name=name + '_3_conv')(x)x = layers.Add(name=name + '_out')([shortcut, x])return x2.堆叠Residual Block
def stack2(x, filters, blocks, stride1=2, name=None):x = block2(x, filters, conv_shortcut=True, name=name + '_block1')for i in range(2, blocks):x = block2(x, filters, name=name + '_block' + str(i))x = block2(x, filters, stride=stride1, name=name + '_block' + str(blocks))return x
3.ResNet50V2架构复现
def ResNet50V2(include_top=True, # 是否包含位于网络顶部的全连接层preact=True, # 是否使用预激活use_bias=True, # 是否对卷积层使用偏置weights='imagenet',input_tensor=None, # 可选的keras张量，用作模型的图像输入input_shape=None,pooling=None,classes=1000, # 用于分类图像的可选类数classifier_activation='softmax'): # 分类层激活函数img_input = layers.Input(shape=input_shape)x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)if not preact:x = layers.BatchNormalization(name='conv1_bn')(x)x = layers.Activation('relu', name='conv1_relu')(x)x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)x = stack2(x, 64, 3, name='conv2')x = stack2(x, 128, 4, name='conv3')x = stack2(x, 256, 6, name='conv4')x = stack2(x, 512, 3, stride1=1, name='conv5')if preact:x = layers.BatchNormalization(name='post_bn')(x)x = layers.Activation('relu', name='post_relu')(x)if include_top:x = layers.GlobalAveragePooling2D(name='avg_pool')(x)x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x)else:if pooling == 'avg':# GlobalAveragePooling2D就是将每张图片的每个通道值各自加起来再求平均，# 最后结果是没有了宽高维度，只剩下个数与平均值两个维度。# 可以理解为变成了多张单像素图片。x = layers.GlobalAveragePooling2D(name='avg_pool')(x)elif pooling == 'max':x = layers.GlobalMaxPooling2D(name='max_pool')(x)model = Model(img_input, x)return model
if __name__ == '__main__':model = ResNet50V2(input_shape=(224, 224, 3))model.summary()
Model: "model"
__________________________________________________________________________________________________Layer (type) Output Shape Param # Connected to
==================================================================================================input_2 (InputLayer) [(None, 224, 224, 3 0 [] )] conv1_pad (ZeroPadding2D) (None, 230, 230, 3) 0 ['input_2[0][0]'] conv1_conv (Conv2D) (None, 112, 112, 64 9472 ['conv1_pad[0][0]'] ) pool1_pad (ZeroPadding2D) (None, 114, 114, 64 0 ['conv1_conv[0][0]'] ) pool1_pool (MaxPooling2D) (None, 56, 56, 64) 0 ['pool1_pad[0][0]'] conv2_block1_preact_bn (BatchN (None, 56, 56, 64) 256 ['pool1_pool[0][0]'] ormalization) conv2_block1_preact_relu (Acti (None, 56, 56, 64) 0 ['conv2_block1_preact_bn[0][0]'] vation) conv2_block1_1_conv (Conv2D) (None, 56, 56, 64) 4096 ['conv2_block1_preact_relu[0][0]'] conv2_block1_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block1_1_conv[0][0]'] ization) conv2_block1_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block1_1_bn[0][0]'] n) conv2_block1_2_pad (ZeroPaddin (None, 58, 58, 64) 0 ['conv2_block1_1_relu[0][0]'] g2D) conv2_block1_2_conv (Conv2D) (None, 56, 56, 64) 36864 ['conv2_block1_2_pad[0][0]'] conv2_block1_2_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block1_2_conv[0][0]'] ization) conv2_block1_2_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block1_2_bn[0][0]'] n) conv2_block1_0_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block1_preact_relu[0][0]'] conv2_block1_3_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block1_2_relu[0][0]'] conv2_block1_out (Add) (None, 56, 56, 256) 0 ['conv2_block1_0_conv[0][0]', 'conv2_block1_3_conv[0][0]'] conv2_block2_preact_bn (BatchN (None, 56, 56, 256) 1024 ['conv2_block1_out[0][0]'] ormalization) conv2_block2_preact_relu (Acti (None, 56, 56, 256) 0 ['conv2_block2_preact_bn[0][0]'] vation) conv2_block2_1_conv (Conv2D) (None, 56, 56, 64) 16384 ['conv2_block2_preact_relu[0][0]'] conv2_block2_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block2_1_conv[0][0]'] ization) conv2_block2_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block2_1_bn[0][0]'] n) conv2_block2_2_pad (ZeroPaddin (None, 58, 58, 64) 0 ['conv2_block2_1_relu[0][0]'] g2D) conv2_block2_2_conv (Conv2D) (None, 56, 56, 64) 36864 ['conv2_block2_2_pad[0][0]'] conv2_block2_2_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block2_2_conv[0][0]'] ization) conv2_block2_2_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block2_2_bn[0][0]'] n) conv2_block2_3_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block2_2_relu[0][0]'] conv2_block2_out (Add) (None, 56, 56, 256) 0 ['conv2_block1_out[0][0]', 'conv2_block2_3_conv[0][0]'] conv2_block3_preact_bn (BatchN (None, 56, 56, 256) 1024 ['conv2_block2_out[0][0]'] ormalization) conv2_block3_preact_relu (Acti (None, 56, 56, 256) 0 ['conv2_block3_preact_bn[0][0]'] vation) conv2_block3_1_conv (Conv2D) (None, 56, 56, 64) 16384 ['conv2_block3_preact_relu[0][0]'] conv2_block3_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block3_1_conv[0][0]'] ization) conv2_block3_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block3_1_bn[0][0]'] n) conv2_block3_2_pad (ZeroPaddin (None, 58, 58, 64) 0 ['conv2_block3_1_relu[0][0]'] g2D) conv2_block3_2_conv (Conv2D) (None, 28, 28, 64) 36864 ['conv2_block3_2_pad[0][0]'] conv2_block3_2_bn (BatchNormal (None, 28, 28, 64) 256 ['conv2_block3_2_conv[0][0]'] ization) conv2_block3_2_relu (Activatio (None, 28, 28, 64) 0 ['conv2_block3_2_bn[0][0]'] n) max_pooling2d_3 (MaxPooling2D) (None, 28, 28, 256) 0 ['conv2_block2_out[0][0]'] conv2_block3_3_conv (Conv2D) (None, 28, 28, 256) 16640 ['conv2_block3_2_relu[0][0]'] conv2_block3_out (Add) (None, 28, 28, 256) 0 ['max_pooling2d_3[0][0]', 'conv2_block3_3_conv[0][0]'] conv3_block1_preact_bn (BatchN (None, 28, 28, 256) 1024 ['conv2_block3_out[0][0]'] ormalization) conv3_block1_preact_relu (Acti (None, 28, 28, 256) 0 ['conv3_block1_preact_bn[0][0]'] vation) conv3_block1_1_conv (Conv2D) (None, 28, 28, 128) 32768 ['conv3_block1_preact_relu[0][0]'] conv3_block1_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block1_1_conv[0][0]'] ization) conv3_block1_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block1_1_bn[0][0]'] n) conv3_block1_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block1_1_relu[0][0]'] g2D) conv3_block1_2_conv (Conv2D) (None, 28, 28, 128) 147456 ['conv3_block1_2_pad[0][0]'] conv3_block1_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block1_2_conv[0][0]'] ization) conv3_block1_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block1_2_bn[0][0]'] n) conv3_block1_0_conv (Conv2D) (None, 28, 28, 512) 131584 ['conv3_block1_preact_relu[0][0]'] conv3_block1_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block1_2_relu[0][0]'] conv3_block1_out (Add) (None, 28, 28, 512) 0 ['conv3_block1_0_conv[0][0]', 'conv3_block1_3_conv[0][0]'] conv3_block2_preact_bn (BatchN (None, 28, 28, 512) 2048 ['conv3_block1_out[0][0]'] ormalization) conv3_block2_preact_relu (Acti (None, 28, 28, 512) 0 ['conv3_block2_preact_bn[0][0]'] vation) conv3_block2_1_conv (Conv2D) (None, 28, 28, 128) 65536 ['conv3_block2_preact_relu[0][0]'] conv3_block2_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block2_1_conv[0][0]'] ization) conv3_block2_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block2_1_bn[0][0]'] n) conv3_block2_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block2_1_relu[0][0]'] g2D) conv3_block2_2_conv (Conv2D) (None, 28, 28, 128) 147456 ['conv3_block2_2_pad[0][0]'] conv3_block2_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block2_2_conv[0][0]'] ization) conv3_block2_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block2_2_bn[0][0]'] n) conv3_block2_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block2_2_relu[0][0]'] conv3_block2_out (Add) (None, 28, 28, 512) 0 ['conv3_block1_out[0][0]', 'conv3_block2_3_conv[0][0]'] conv3_block3_preact_bn (BatchN (None, 28, 28, 512) 2048 ['conv3_block2_out[0][0]'] ormalization) conv3_block3_preact_relu (Acti (None, 28, 28, 512) 0 ['conv3_block3_preact_bn[0][0]'] vation) conv3_block3_1_conv (Conv2D) (None, 28, 28, 128) 65536 ['conv3_block3_preact_relu[0][0]'] conv3_block3_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block3_1_conv[0][0]'] ization) conv3_block3_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block3_1_bn[0][0]'] n) conv3_block3_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block3_1_relu[0][0]'] g2D) conv3_block3_2_conv (Conv2D) (None, 28, 28, 128) 147456 ['conv3_block3_2_pad[0][0]'] conv3_block3_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block3_2_conv[0][0]'] ization) conv3_block3_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block3_2_bn[0][0]'] n) conv3_block3_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block3_2_relu[0][0]'] conv3_block3_out (Add) (None, 28, 28, 512) 0 ['conv3_block2_out[0][0]', 'conv3_block3_3_conv[0][0]'] conv3_block4_preact_bn (BatchN (None, 28, 28, 512) 2048 ['conv3_block3_out[0][0]'] ormalization) conv3_block4_preact_relu (Acti (None, 28, 28, 512) 0 ['conv3_block4_preact_bn[0][0]'] vation) conv3_block4_1_conv (Conv2D) (None, 28, 28, 128) 65536 ['conv3_block4_preact_relu[0][0]'] conv3_block4_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block4_1_conv[0][0]'] ization) conv3_block4_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block4_1_bn[0][0]'] n) conv3_block4_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block4_1_relu[0][0]'] g2D) conv3_block4_2_conv (Conv2D) (None, 14, 14, 128) 147456 ['conv3_block4_2_pad[0][0]'] conv3_block4_2_bn (BatchNormal (None, 14, 14, 128) 512 ['conv3_block4_2_conv[0][0]'] ization) conv3_block4_2_relu (Activatio (None, 14, 14, 128) 0 ['conv3_block4_2_bn[0][0]'] n) max_pooling2d_4 (MaxPooling2D) (None, 14, 14, 512) 0 ['conv3_block3_out[0][0]'] conv3_block4_3_conv (Conv2D) (None, 14, 14, 512) 66048 ['conv3_block4_2_relu[0][0]'] conv3_block4_out (Add) (None, 14, 14, 512) 0 ['max_pooling2d_4[0][0]', 'conv3_block4_3_conv[0][0]'] conv4_block1_preact_bn (BatchN (None, 14, 14, 512) 2048 ['conv3_block4_out[0][0]'] ormalization) conv4_block1_preact_relu (Acti (None, 14, 14, 512) 0 ['conv4_block1_preact_bn[0][0]'] vation) conv4_block1_1_conv (Conv2D) (None, 14, 14, 256) 131072 ['conv4_block1_preact_relu[0][0]'] conv4_block1_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block1_1_conv[0][0]'] ization) conv4_block1_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block1_1_bn[0][0]'] n) conv4_block1_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block1_1_relu[0][0]'] g2D) conv4_block1_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block1_2_pad[0][0]'] conv4_block1_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block1_2_conv[0][0]'] ization) conv4_block1_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block1_2_bn[0][0]'] n) conv4_block1_0_conv (Conv2D) (None, 14, 14, 1024 525312 ['conv4_block1_preact_relu[0][0]') ] conv4_block1_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block1_2_relu[0][0]'] ) conv4_block1_out (Add) (None, 14, 14, 1024 0 ['conv4_block1_0_conv[0][0]', ) 'conv4_block1_3_conv[0][0]'] conv4_block2_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block1_out[0][0]'] ormalization) ) conv4_block2_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block2_preact_bn[0][0]'] vation) ) conv4_block2_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block2_preact_relu[0][0]'] conv4_block2_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block2_1_conv[0][0]'] ization) conv4_block2_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block2_1_bn[0][0]'] n) conv4_block2_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block2_1_relu[0][0]'] g2D) conv4_block2_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block2_2_pad[0][0]'] conv4_block2_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block2_2_conv[0][0]'] ization) conv4_block2_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block2_2_bn[0][0]'] n) conv4_block2_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block2_2_relu[0][0]'] ) conv4_block2_out (Add) (None, 14, 14, 1024 0 ['conv4_block1_out[0][0]', ) 'conv4_block2_3_conv[0][0]'] conv4_block3_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block2_out[0][0]'] ormalization) ) conv4_block3_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block3_preact_bn[0][0]'] vation) ) conv4_block3_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block3_preact_relu[0][0]'] conv4_block3_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block3_1_conv[0][0]'] ization) conv4_block3_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block3_1_bn[0][0]'] n) conv4_block3_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block3_1_relu[0][0]'] g2D) conv4_block3_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block3_2_pad[0][0]'] conv4_block3_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block3_2_conv[0][0]'] ization) conv4_block3_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block3_2_bn[0][0]'] n) conv4_block3_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block3_2_relu[0][0]'] ) conv4_block3_out (Add) (None, 14, 14, 1024 0 ['conv4_block2_out[0][0]', ) 'conv4_block3_3_conv[0][0]'] conv4_block4_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block3_out[0][0]'] ormalization) ) conv4_block4_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block4_preact_bn[0][0]'] vation) ) conv4_block4_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block4_preact_relu[0][0]'] conv4_block4_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block4_1_conv[0][0]'] ization) conv4_block4_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block4_1_bn[0][0]'] n) conv4_block4_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block4_1_relu[0][0]'] g2D) conv4_block4_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block4_2_pad[0][0]'] conv4_block4_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block4_2_conv[0][0]'] ization) conv4_block4_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block4_2_bn[0][0]'] n) conv4_block4_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block4_2_relu[0][0]'] ) conv4_block4_out (Add) (None, 14, 14, 1024 0 ['conv4_block3_out[0][0]', ) 'conv4_block4_3_conv[0][0]'] conv4_block5_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block4_out[0][0]'] ormalization) ) conv4_block5_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block5_preact_bn[0][0]'] vation) ) conv4_block5_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block5_preact_relu[0][0]'] conv4_block5_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block5_1_conv[0][0]'] ization) conv4_block5_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block5_1_bn[0][0]'] n) conv4_block5_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block5_1_relu[0][0]'] g2D) conv4_block5_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block5_2_pad[0][0]'] conv4_block5_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block5_2_conv[0][0]'] ization) conv4_block5_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block5_2_bn[0][0]'] n) conv4_block5_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block5_2_relu[0][0]'] ) conv4_block5_out (Add) (None, 14, 14, 1024 0 ['conv4_block4_out[0][0]', ) 'conv4_block5_3_conv[0][0]'] conv4_block6_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block5_out[0][0]'] ormalization) ) conv4_block6_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block6_preact_bn[0][0]'] vation) ) conv4_block6_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block6_preact_relu[0][0]'] conv4_block6_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block6_1_conv[0][0]'] ization) conv4_block6_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block6_1_bn[0][0]'] n) conv4_block6_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block6_1_relu[0][0]'] g2D) conv4_block6_2_conv (Conv2D) (None, 7, 7, 256) 589824 ['conv4_block6_2_pad[0][0]'] conv4_block6_2_bn (BatchNormal (None, 7, 7, 256) 1024 ['conv4_block6_2_conv[0][0]'] ization) conv4_block6_2_relu (Activatio (None, 7, 7, 256) 0 ['conv4_block6_2_bn[0][0]'] n) max_pooling2d_5 (MaxPooling2D) (None, 7, 7, 1024) 0 ['conv4_block5_out[0][0]'] conv4_block6_3_conv (Conv2D) (None, 7, 7, 1024) 263168 ['conv4_block6_2_relu[0][0]'] conv4_block6_out (Add) (None, 7, 7, 1024) 0 ['max_pooling2d_5[0][0]', 'conv4_block6_3_conv[0][0]'] conv5_block1_preact_bn (BatchN (None, 7, 7, 1024) 4096 ['conv4_block6_out[0][0]'] ormalization) conv5_block1_preact_relu (Acti (None, 7, 7, 1024) 0 ['conv5_block1_preact_bn[0][0]'] vation) conv5_block1_1_conv (Conv2D) (None, 7, 7, 512) 524288 ['conv5_block1_preact_relu[0][0]'] conv5_block1_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block1_1_conv[0][0]'] ization) conv5_block1_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block1_1_bn[0][0]'] n) conv5_block1_2_pad (ZeroPaddin (None, 9, 9, 512) 0 ['conv5_block1_1_relu[0][0]'] g2D) conv5_block1_2_conv (Conv2D) (None, 7, 7, 512) 2359296 ['conv5_block1_2_pad[0][0]'] conv5_block1_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block1_2_conv[0][0]'] ization) conv5_block1_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block1_2_bn[0][0]'] n) conv5_block1_0_conv (Conv2D) (None, 7, 7, 2048) 2099200 ['conv5_block1_preact_relu[0][0]'] conv5_block1_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block1_2_relu[0][0]'] conv5_block1_out (Add) (None, 7, 7, 2048) 0 ['conv5_block1_0_conv[0][0]', 'conv5_block1_3_conv[0][0]'] conv5_block2_preact_bn (BatchN (None, 7, 7, 2048) 8192 ['conv5_block1_out[0][0]'] ormalization) conv5_block2_preact_relu (Acti (None, 7, 7, 2048) 0 ['conv5_block2_preact_bn[0][0]'] vation) conv5_block2_1_conv (Conv2D) (None, 7, 7, 512) 1048576 ['conv5_block2_preact_relu[0][0]'] conv5_block2_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block2_1_conv[0][0]'] ization) conv5_block2_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block2_1_bn[0][0]'] n) conv5_block2_2_pad (ZeroPaddin (None, 9, 9, 512) 0 ['conv5_block2_1_relu[0][0]'] g2D) conv5_block2_2_conv (Conv2D) (None, 7, 7, 512) 2359296 ['conv5_block2_2_pad[0][0]'] conv5_block2_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block2_2_conv[0][0]'] ization) conv5_block2_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block2_2_bn[0][0]'] n) conv5_block2_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block2_2_relu[0][0]'] conv5_block2_out (Add) (None, 7, 7, 2048) 0 ['conv5_block1_out[0][0]', 'conv5_block2_3_conv[0][0]'] conv5_block3_preact_bn (BatchN (None, 7, 7, 2048) 8192 ['conv5_block2_out[0][0]'] ormalization) conv5_block3_preact_relu (Acti (None, 7, 7, 2048) 0 ['conv5_block3_preact_bn[0][0]'] vation) conv5_block3_1_conv (Conv2D) (None, 7, 7, 512) 1048576 ['conv5_block3_preact_relu[0][0]'] conv5_block3_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block3_1_conv[0][0]'] ization) conv5_block3_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block3_1_bn[0][0]'] n) conv5_block3_2_pad (ZeroPaddin (None, 9, 9, 512) 0 ['conv5_block3_1_relu[0][0]'] g2D) conv5_block3_2_conv (Conv2D) (None, 7, 7, 512) 2359296 ['conv5_block3_2_pad[0][0]'] conv5_block3_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block3_2_conv[0][0]'] ization) conv5_block3_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block3_2_bn[0][0]'] n) conv5_block3_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block3_2_relu[0][0]'] conv5_block3_out (Add) (None, 7, 7, 2048) 0 ['conv5_block2_out[0][0]', 'conv5_block3_3_conv[0][0]'] post_bn (BatchNormalization) (None, 7, 7, 2048) 8192 ['conv5_block3_out[0][0]'] post_relu (Activation) (None, 7, 7, 2048) 0 ['post_bn[0][0]'] avg_pool (GlobalAveragePooling (None, 2048) 0 ['post_relu[0][0]'] 2D) predictions (Dense) (None, 1000) 2049000 ['avg_pool[0][0]'] ==================================================================================================
Total params: 25,613,800
Trainable params: 25,568,360
Non-trainable params: 45,440
__________________________________________________________________________________________________
model.compile(optimizer="adam",loss='sparse_categorical_crossentropy',metrics=['accuracy'])
五、训练模型
epochs = 10history = model.fit(train_ds,validation_data=val_ds,epochs=epochs
)
Epoch 1/102025-02-14 10:51:34.188825: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype int32 and shape [452][[{{node Placeholder/_4}}]]
2025-02-14 10:51:34.189120: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_0' with dtype string and shape [452][[{{node Placeholder/_0}}]]57/57 [==============================] - ETA: 0s - loss: 1.4427 - accuracy: 0.53102025-02-14 10:52:07.689698: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_4' with dtype int32 and shape [113][[{{node Placeholder/_4}}]]
2025-02-14 10:52:07.689827: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_0' with dtype string and shape [113][[{{node Placeholder/_0}}]]57/57 [==============================] - 36s 613ms/step - loss: 1.4427 - accuracy: 0.5310 - val_loss: 994.0645 - val_accuracy: 0.3186
Epoch 2/10
57/57 [==============================] - 34s 599ms/step - loss: 0.8882 - accuracy: 0.6482 - val_loss: 16.8545 - val_accuracy: 0.3805
Epoch 3/10
57/57 [==============================] - 34s 599ms/step - loss: 0.8002 - accuracy: 0.6925 - val_loss: 4.0983 - val_accuracy: 0.4602
Epoch 4/10
57/57 [==============================] - 34s 599ms/step - loss: 0.6916 - accuracy: 0.7412 - val_loss: 4.0794 - val_accuracy: 0.3540
Epoch 5/10
57/57 [==============================] - 34s 600ms/step - loss: 0.6951 - accuracy: 0.7456 - val_loss: 83.9201 - val_accuracy: 0.3186
Epoch 6/10
57/57 [==============================] - 34s 604ms/step - loss: 0.6024 - accuracy: 0.7655 - val_loss: 3.4875 - val_accuracy: 0.4425
Epoch 7/10
57/57 [==============================] - 34s 600ms/step - loss: 0.5214 - accuracy: 0.7965 - val_loss: 1.2221 - val_accuracy: 0.6991
Epoch 8/10
57/57 [==============================] - 35s 623ms/step - loss: 0.4850 - accuracy: 0.8142 - val_loss: 1.4684 - val_accuracy: 0.4867
Epoch 9/10
57/57 [==============================] - 35s 613ms/step - loss: 0.4335 - accuracy: 0.8252 - val_loss: 1.5076 - val_accuracy: 0.6814
Epoch 10/10
57/57 [==============================] - 35s 615ms/step - loss: 0.3424 - accuracy: 0.8850 - val_loss: 1.7519 - val_accuracy: 0.6903
六、结果可视化
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.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()
总结
本周项目手动搭建了手动搭建了ResNet50V2模型，与ResNet50模型相比，残差模型将BN和ReLU进行了前置，在一定程度上有效地提升了模型的准确率。但是模型效果不是很理想，后续需要进一步优化。