MOOC TensorFlow入门实操课程代码回顾总结（一）

最新推荐文章于 2023-12-27 17:30:00 发布

荣仔！最靓的仔！

最新推荐文章于 2023-12-27 17:30:00 发布

阅读量7.1k

点赞数 4

分类专栏： TensorFlow 实战系列文章标签： tensorflow python 神经网络深度学习 MOOC

本文链接：https://blog.csdn.net/IT_charge/article/details/113538940

版权

TensorFlow 实战系列专栏收录该内容

5 篇文章 6 订阅

订阅专栏

欢迎来到TensorFlow入门实操课程的学习

MOOC TensorFlow入门实操课程代码回顾总结（二）
MOOC TensorFlow入门实操课程代码回顾总结（三）

注：

用于表示python代码

粘贴运行结果

1 TensotFlow深度学习的第一门课程

1.1 查看tensorflow版本

import tensorflow as tf
print(tf.__version__)

2.3.0

1.2 使用tensorflow编写的第一个示例

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
import tensorflow as tf
# 构建模型
model = keras.Sequential([keras.layers.Dense(units=1, input_shape=[1])])
model.compile(optimizer='sgd', loss='mean_squared_error')
# 准备训练数据
xs = np.array([-1.0, 0.0, 1.0, 2.0, 3.0, 4.0], dtype=float)
ys = np.array([-3.0, -1.0, 1.0, 3.0, 5.0, 7.0], dtype=float)
# 训练模型
model.fit(xs, ys, epochs=500)

# 使用模型
print(model.predict([10.0]))

[[18.976088]]

2 计算机视觉介绍

2.1 加载Fashion MNIST数据集

from tensorflow import keras
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

train_images.shape

(60000, 28, 28)

test_images.shape

(10000, 28, 28)

train_images[0]

train_labels.shape

(60000,)

train_labels[:5]

array([9, 0, 0, 3, 0], dtype=uint8)

# 查看图片样式
import matplotlib.pyplot as plt
plt.imshow(train_images[0])

<matplotlib.image.AxesImage at 0x7f33c40a4350>

# 查看图片样式
import matplotlib.pyplot as plt
plt.imshow(train_images[7])

<matplotlib.image.AxesImage at 0x7f33c403abd0>

2.2 构造神经元网络模型

model = keras.Sequential()
model.add(keras.layers.Flatten(input_shape=(28, 28)))
model.add(keras.layers.Dense(128, activation=tf.nn.relu))
model.add(keras.layers.Dense(10, activation=tf.nn.softmax))

model.summary()
# (28*28+1)*128=100480
# (128+1)*10=1290
# 加1是有1个bias，但最终输出层没有

train_images = train_images/255  #归一化
model.compile(optimizer=tf.optimizers.Adam(), loss=tf.losses.sparse_categorical_crossentropy, metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=5)
# 训练没有问题。正在对1875批次（每批次32张图像）而不是1875张图像进行模型训练。   1875 * 32 = 60000张图像

test_images_scaled = test_images/255
model.evaluate(test_images_scaled,test_labels)

2.3 训练和评估模型

0 T-shirt/top(体恤) 1 Trouser(裤子) 2 Pullover(套头衫) 3 Dress(连衣裙) 4 Coat(外套) 5 Sandal(凉鞋) 6 Shirt(衬衫) 7 Sneaker(运动鞋) 8 Bag(袋子) 9 Ankle boot(短靴）

print(np.argmax(model.predict((test_images[0]/255).reshape(1,28,28,1))))
print(test_labels[0])
plt.imshow(test_images[0])

9
9
<matplotlib.image.AxesImage at 0x7f332ab55e50>

2.4 自动终止训练

class myCallback(tf.keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs={}):
        if(logs.get('loss')<0.4):
            print("\nLoss is low so cancelling training!")
            self.model.stop_training = True

callbacks = myCallback()
mnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()
training_images_scaled = training_images/255.0
test_images_scaled = test_images/255.0
model = tf.keras.models.Sequential([tf.keras.layers.Flatten(),tf.keras.layers.Dense(512,activation=tf.nn.relu),tf.keras.layers.Dense(10,activation=tf.nn.softmax)])
model.compile(optimizer='adam',loss='sparse_categorical_crossentropy')
model.fit(training_images_scaled, training_labels, epochs=5, callbacks=[callbacks])

3 卷积神经网络

3.1 卷积网络程序

import tensorflow as tf
from tensorflow import keras

# 前提有一个全连接的神经元网络
fashion_mnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels), (test_images, test_labels) = fashion_mnist.load_data()

# 卷积神经网络就是在全连接网络上面，增加这样四层
model = keras.Sequential()
model.add(keras.layers.Conv2D(64,(3,3),activation='relu',input_shape=(28,28,1)))
model.add(keras.layers.MaxPool2D(2,2))
model.add(keras.layers.Conv2D(64,(3,3),activation='relu'))
model.add(keras.layers.MaxPool2D(2,2))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(128,activation=tf.nn.relu))
model.add(keras.layers.Dense(10,activation=tf.nn.softmax))

training_images_scaled = training_images/255
model.compile(optimizer=tf.optimizers.Adam(), loss=tf.losses.sparse_categorical_crossentropy, metrics=['accuracy'])
model.fit(training_images_scaled.reshape(-1,28,28,1), training_labels,epochs=5)

3.2 卷积网络结构

model.summary()

import matplotlib.pyplot as plt

layer_outputs = [layer.output for layer in model.layers]
activation_model = tf.keras.models.Model(inputs = model.input, outputs = layer_outputs)
pred = activation_model.predict(test_images[0].reshape(1,28,28,1))

pred

plt.imshow(pred[0][0,:,:,1])

<matplotlib.image.AxesImage at 0x7ff09c457710>

plt.imshow(pred[0][0,:,:,2])

<matplotlib.image.AxesImage at 0x7ff0e41afe90>

4 更复杂的图像应用

4.1 下载数据集

!wget --no-check-certificate \ https://storage.googleapis.com/laurencemoroney-blog.appspot.com/validation-horse-or-human.zip -o /tmp/validation-harse-or-human.zip
!wget --no-check-certificate \ https://storage.googleapis.com/laurencemoroney-blog.appspot.com/horse-or-human.zip -o /tmp/harse-or-human.zip

4.2 ImageDataGenerator

from tensorflow.keras.preprocessing.image import ImageDataGenerator

# 创建两个数据生成器，指定scaling范围 0～1
train_datagen = ImageDataGenerator(rescale=1/255)
validation_datagen = ImageDataGenerator(rescale=1/255)

# 指向训练数据文件夹
train_generator = train_datagen.flow_from_directory(
        '/home/zzr/data/horse-or-human', # 训练数据所在文件夹
        target_size=(300,300),           # 指定输出尺寸
        batch_size=32,
        class_mode='binary')             # 指定二分类

# 指向测试数据文件夹
validation_generator = validation_datagen.flow_from_directory(
        '/home/zzr/data/validation-horse-or-human',  # 测试数据所在文件夹
        target_size=(300,300),                       # 指定输出尺寸
        batch_size=32,
        class_mode='binary')                         # 指定二分类

Found 1027 images belonging to 2 classes.
Found 256 images belonging to 2 classes.

4.3 构建并训练模型

model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(16,(3,3),activation='relu',input_shape=(300,300,3)),
    tf.keras.layers.MaxPool2D(2,2),
    tf.keras.layers.Conv2D(32,(3,3),activation='relu'),
    tf.keras.layers.MaxPool2D(2,2),
    tf.keras.layers.Conv2D(64,(3,3),activation='relu'),
    tf.keras.layers.MaxPool2D(2,2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512,activation='relu'),
    tf.keras.layers.Dense(1,activation='sigmoid')
])

model.summary()

# Optimizers优化函数这里使用的是RMS
from tensorflow.keras.optimizers import RMSprop

model.compile(loss='binary_crossentropy',
             optimizer=RMSprop(lr=0.001),
             metrics=['acc'])
history = model.fit(
        train_generator,
        epochs=15,
        verbose=1,
        validation_data=validation_generator,
        validation_steps=8)

4.4 优化模型参数

pip install -U keras-tuner

import os
from kerastuner.tuners import Hyperband
from kerastuner.engine.hyperparameters import HyperParameters
# 创建两个数据生成器，指定scaling范围 0～1
train_datagen = ImageDataGenerator(rescale=1/255)
validation_datagen = ImageDataGenerator(rescale=1/255)

# 指向训练数据文件夹
train_generator = train_datagen.flow_from_directory(
        '/home/zzr/data/horse-or-human', # 训练数据所在文件夹
        target_size=(150,150),           # 指定输出尺寸
        batch_size=32,
        class_mode='binary')             # 指定二分类

# 指向测试数据文件夹
validation_generator = validation_datagen.flow_from_directory(
        '/home/zzr/data/validation-horse-or-human',  # 测试数据所在文件夹
        target_size=(150,150),                       # 指定输出尺寸
        batch_size=32,
        class_mode='binary')                         # 指定二分类

hp = HyperParameters()

def build_model(hp):
    model = tf.keras.models.Sequential()
    model.add(tf.keras.layers.Conv2D(hp.Choice('num_filters_layer0',values=[16,64],default=16),(3,3),activation='relu',input_shape=(150,150,3)))
    model.add(tf.keras.layers.MaxPooling2D(2,2))
    for i in range(hp.Int("num_conv_layers",1,3)):
        model.add(tf.keras.layers.Conv2D(hp.Choice(f'num_filters_layer{i}',values=[16,64],default=16),(3,3),activation='relu'))
        model.add(tf.keras.layers.MaxPooling2D(2,2))
    model.add(tf.keras.layers.Flatten())
    model.add(tf.keras.layers.Dense(hp.Int('hidden_units',128,512,step=32),activation='relu'))
    model.add(tf.keras.layers.Dense(1,activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer=RMSprop(lr=0.001), metrics=['acc'])
    return model

tuner = Hyperband(
    build_model,
    objective='val_acc',
    max_epochs=15,
    directory='horse_human_params',
    hyperparameters=hp,
    project_name='my_horse_human_project'
)

tuner.search(train_generator,epochs=10,validation_data=validation_generator)

Trial 30 Complete [00h 02m 53s]
val_acc: 0.88671875

Best val_acc So Far: 0.9375 Total elapsed time: 00h 33m 33s
INFO:tensorflow:Oracle triggered exit

best_hps=tuner.get_best_hyperparameters(1)[0]
print(best_hps.values)
model=tuner.hypermodel.build(best_hps)
model.summary()