Tensorflow学习笔记（二）Tensorflow keras实战 --tf.keras

使用tf.keras进行模型的搭建   

用到的深度学习的理论知识包括分类问题、回归问题、神经网络、损失函数、激活函数、dropout、批归一化、深度神经网络、Wide&Deep模型、密集特征、稀疏特征、超参数搜索等及其在图像分类、房价预测上的实现。单就这些知识来说，如果前期学过深度学习或者是看过Andrew Ng的deep learning.ai课程，那么应该很好理解，本文主要是总结一下tf.keras在模型搭建时的使用

一个分类模型的例子：

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

输出 ： 2.0.0-alpha0 sys.version_info(major=3, minor=7, micro=3, releaselevel='final', serial=0) matplotlib 3.0.3 numpy 1.16.2 pandas 0.24.2 sklearn 0.20.3 tensorflow 2.0.0-alpha0 tensorflow.python.keras.api._v2.keras 2.2.4-tf

fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

print(x_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

(5000, 28, 28) (5000,) (55000, 28, 28) (55000,) (10000, 28, 28) (10000,)

# tf.keras.models.Sequential()

model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28, 28]))
for _ in range(20):
    model.add(keras.layers.Dense(100, activation="selu"))
model.add(keras.layers.AlphaDropout(rate=0.5))
                                      # AlphaDropout: 1. 均值和方差不变 2. 归一化性质也不变
                                      # model.add(keras.layers.Dropout(rate=0.5))
model.add(keras.layers.Dense(10, activation="softmax"))   #多分类

model.compile(loss="sparse_categorical_crossentropy",
              optimizer = "sgd",
              metrics = ["accuracy"])

 

# Tensorboard, earlystopping, ModelCheckpoint

logdir = './dnn-selu-dropout-callbacks'
if not os.path.exists(logdir):
    os.mkdir(logdir)
output_model_file = os.path.join(logdir,
                                 "fashion_mnist_model.h5")

callbacks = [
    keras.callbacks.TensorBoard(logdir),
    keras.callbacks.ModelCheckpoint(output_model_file,
                                    save_best_only = True),
    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
history = model.fit(x_train_scaled, y_train, epochs=10,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

 

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()

plot_learning_curves(history)

# 1. 参数众多，训练不充分
# 2. 梯度消失 -> 链式法则 -> 复合函数f(g(x))
#    selu缓解梯度消失

 

model.evaluate(x_test_scaled, y_test)