本文为[P365天深度学习训练营](https://mp.weixin.qq.com/s/0 dvHCa0oFnW8SCp3 JpzKxg)中的学习记录博客
原作者:[K同学啊](https://mtyjkh.blog.csdn.net/)
一、前期工作
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)
tf.config.set_visible_devices(gpus[0],"GPU")
2.导入数据
import matplotlib.pyplot as plt
plt.rcParams['axes.unicode_minus'] = False
import os, PIL, pathlib
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers, models
data_dir = './bird_photos'
data_dir = pathlib.Path(data_dir)image_count = len(list(data_dir.glob('*/*')))
print("The number of images: ", image_count)
二、数据处理
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_width = 224
img_height = 224 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
)
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
)
class_names = train_ds.class_names
print(class_names)
2.可视化数据
plt.figure(figsize=(10,5))
plt.suptitle("data showing")
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")) 
3.再次检查数据
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break
4.配置数据集
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)三、残差网络(ResNet)介绍
1. 残差网络解决了什么
残差网络是为了解决神经网络隐藏层过多时，而引起的网络退化问题。退化(degradation)问题是指：当网络隐藏层变多时，网络的准确度达到饱和然后急剧退化，而且这个退化不是由于过拟合引起的。
2. ResNet-50介绍
ResNet-.50有两个基本的块,分别名为Conv Block和Identity Block
四、构建ResNet-50网络模型
from keras import layers
from keras.models import Model
from keras.layers import Input, Activation, BatchNormalization, Flatten
from keras.layers import Dense, Conv2D, MaxPooling2D, ZeroPadding2D, AveragePooling2D
def identity_block(input_tensor, kernel_size, filters, stage, block):
filters1, filters2, filters3 = filters
name_base = str(stage) + block + '_identity_block_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
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=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')
model.load_weights("/content/drive/MyDrive/Colab Notebooks/第8天/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 (ZeroPadd (None, 230, 230, 3) 0 ['input_2[0][0]']
ing2D)
conv1 (Conv2D) (None, 112, 112, 64) 9472 ['zero_padding2d_1[0][0]']
bn_conv1 (BatchNormalizati (None, 112, 112, 64) 256 ['conv1[0][0]']
on)
activation_1 (Activation) (None, 112, 112, 64) 0 ['bn_conv1[0][0]']
max_pooling2d_1 (MaxPoolin (None, 55, 55, 64) 0 ['activation_1[0][0]']
g2D)
2a_conv_block_conv1 (Conv2 (None, 55, 55, 64) 4160 ['max_pooling2d_1[0][0]']
D)
2a_conv_block_bn1 (BatchNo (None, 55, 55, 64) 256 ['2a_conv_block_conv1[0][0]']
rmalization)
2a_conv_block_relu1 (Activ (None, 55, 55, 64) 0 ['2a_conv_block_bn1[0][0]']
ation)
2a_conv_block_conv2 (Conv2 (None, 55, 55, 64) 36928 ['2a_conv_block_relu1[0][0]']
D)
2a_conv_block_bn2 (BatchNo (None, 55, 55, 64) 256 ['2a_conv_block_conv2[0][0]']
rmalization)
2a_conv_block_relu2 (Activ (None, 55, 55, 64) 0 ['2a_conv_block_bn2[0][0]']
ation)
2a_conv_block_conv3 (Conv2 (None, 55, 55, 256) 16640 ['2a_conv_block_relu2[0][0]']
D)
2a_conv_block_res_conv (Co (None, 55, 55, 256) 16640 ['max_pooling2d_1[0][0]']
nv2D)
2a_conv_block_bn3 (BatchNo (None, 55, 55, 256) 1024 ['2a_conv_block_conv3[0][0]']
rmalization)
2a_conv_block_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_bn[0][0]']
2a_conv_block_relu4 (Activ (None, 55, 55, 256) 0 ['2a_conv_block_add[0][0]']
ation)
2b_identity_block_block_co (None, 55, 55, 64) 16448 ['2a_conv_block_relu4[0][0]']
nv1 (Conv2D)
2b_identity_block_block_bn (None, 55, 55, 64) 256 ['2b_identity_block_block_conv
1 (BatchNormalization) 1[0][0]']
2b_identity_block_block_re (None, 55, 55, 64) 0 ['2b_identity_block_block_bn1[
lu1 (Activation) 0][0]']
2b_identity_block_block_co (None, 55, 55, 64) 36928 ['2b_identity_block_block_relu
nv2 (Conv2D) 1[0][0]']
2b_identity_block_block_bn (None, 55, 55, 64) 256 ['2b_identity_block_block_conv
2 (BatchNormalization) 2[0][0]']
2b_identity_block_block_re (None, 55, 55, 64) 0 ['2b_identity_block_block_bn2[
lu2 (Activation) 0][0]']
2b_identity_block_block_co (None, 55, 55, 256) 16640 ['2b_identity_block_block_relu
nv3 (Conv2D) 2[0][0]']
2b_identity_block_block_bn (None, 55, 55, 256) 1024 ['2b_identity_block_block_conv
3 (BatchNormalization) 3[0][0]']
2b_identity_block_block_ad (None, 55, 55, 256) 0 ['2b_identity_block_block_bn3[
d (Add) 0][0]',
'2a_conv_block_relu4[0][0]']
2b_identity_block_block_re (None, 55, 55, 256) 0 ['2b_identity_block_block_add[
lu4 (Activation) 0][0]']
2c_identity_block_block_co (None, 55, 55, 64) 16448 ['2b_identity_block_block_relu
nv1 (Conv2D) 4[0][0]']
2c_identity_block_block_bn (None, 55, 55, 64) 256 ['2c_identity_block_block_conv
1 (BatchNormalization) 1[0][0]']
2c_identity_block_block_re (None, 55, 55, 64) 0 ['2c_identity_block_block_bn1[
lu1 (Activation) 0][0]']
2c_identity_block_block_co (None, 55, 55, 64) 36928 ['2c_identity_block_block_relu
nv2 (Conv2D) 1[0][0]']
2c_identity_block_block_bn (None, 55, 55, 64) 256 ['2c_identity_block_block_conv
2 (BatchNormalization) 2[0][0]']
2c_identity_block_block_re (None, 55, 55, 64) 0 ['2c_identity_block_block_bn2[
lu2 (Activation) 0][0]']
2c_identity_block_block_co (None, 55, 55, 256) 16640 ['2c_identity_block_block_relu
nv3 (Conv2D) 2[0][0]']
2c_identity_block_block_bn (None, 55, 55, 256) 1024 ['2c_identity_block_block_conv
3 (BatchNormalization) 3[0][0]']
2c_identity_block_block_ad (None, 55, 55, 256) 0 ['2c_identity_block_block_bn3[
d (Add) 0][0]',
'2b_identity_block_block_relu
4[0][0]']
2c_identity_block_block_re (None, 55, 55, 256) 0 ['2c_identity_block_block_add[
lu4 (Activation) 0][0]']
3a_conv_block_conv1 (Conv2 (None, 28, 28, 128) 32896 ['2c_identity_block_block_relu
D) 4[0][0]']
3a_conv_block_bn1 (BatchNo (None, 28, 28, 128) 512 ['3a_conv_block_conv1[0][0]']
rmalization)
最低0.47元/天 解锁文章
扫一扫
9078
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
