tf.keras入门(1) Basic Classification（Fashion MNIST数据集）

基本分类（Fashion MNIST）

使用tf.keras ，是一种在TensorFlow中构建和训练模型的高阶api

本指南使用 Fashion MNIST 数据集，其中包含 70000 张灰度图像，涵盖 10 个类别。以下图像显示了单件服饰在较低分辨率（28x28 像素）下的效果：

主要接口解释

keras.datasets 自带的一些数据集

tf.nn.relu 使用relu激活函数

tf.nn.softmax 使用sotfmax激活函数

tf.train.AdamOptimizer() 使用AdamOptimizer 优化算法

keras.layers.Flatten

keras.layers.Dense

model = keras.Sequential([])

model.compile(optimizer = tf.train.AdamOptimizer(), ​ loss='sparse_categorical_crossentropy', ​ metrics = ['accuracy'])

• 这里$sparse\_categorical\_crossentropy$ 和 $categorical\_crossentropy$ 的区别是：

  如果你的Label是one-hot encoding的就用$categorical\_crossentropy$；

  如果Label是一个integer，就用$sparse\_categorical\_crossentropy$

model.fit(train_images, train_labels, epochs = 5)

model.evaluate(test_images, test_labels)

img = (np.expand_dims(img,0))

• np.expand_dims的用法：

>>> x = np.array([1,2])
>>> x.shape
(2,)


>>> y = np.expand_dims(x, axis=0)
>>> y
array([[1, 2]])
>>> y.shape
(1, 2)


>>> y = np.expand_dims(x, axis=1)  # Equivalent to x[:,newaxis]
>>> y
array([[1],
       [2]])
>>> y.shape
(2, 1)

predictions_single = model.predict(img)

可以一次性对样本批次或样本集进行预测。因此，即使我们使用单个图像，仍需要将其添加到列表中：

cross entropy

​ $softmax$函数最常用的损失函数就是交叉熵。

​ 如何理解该函数呢？

​ 首先我们先来了解一下信息熵的概念，其衡量的是一种”意外程度“，计算公式为：
$$H(x)=-\sum _{i=1}^{n}p(x_i)lo{g}_{2}P(x_i),whichi=1,2,\cdots ,n$$
​ 举个例子来进一步说明，现在中美两国打乒乓球比赛，历史交手共64次，其中中国胜利63次。那这次中国胜利的信息量是$-lo{g}_2\frac{63}{64}\approx 0.023$ 而美国队是$-lo{g}_2\frac{1}{64}=6$ 所以，比赛结果的信息熵为：
$$0.023\ast \frac{63}{64}+6\ast \frac{1}{64}=0.1164$$
这个熵还是比较小的，即结果蛮确定的，结果很意外的概率比较小！

…后面推导待补

完整代码

load_data.py

from tensorflow.python.keras.utils import get_file
import gzip
import numpy as np

def load_datas():
    base = r"file:///C:/Users/your_username/Desktop/test_tensor/data/fashion-mnist/"
    files = [
        'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
        't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'
    ]
    paths = []
    for fname in files:
        paths.append(get_file(fname, origin=base + fname))

    with gzip.open(paths[0], 'rb') as lbpath:
        y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)

    with gzip.open(paths[1], 'rb') as imgpath:
        x_train = np.frombuffer(
            imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)

    with gzip.open(paths[2], 'rb') as lbpath:
        y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)

    with gzip.open(paths[3], 'rb') as imgpath:
        x_test = np.frombuffer(
            imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)

    return (x_train, y_train), (x_test, y_test)

基本分类.py

import tensorflow as tf 
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
import load_data

fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = load_data.load_datas()
train_images = train_images / 255.0
test_images = test_images / 255.0
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

# print(train_images.shape)

# plt.figure()
# plt.imshow(train_images[0])
# plt.colorbar()
# plt.grid(False)
# plt.figure(figsize=(10,10))
# for i in range(25):
#     plt.subplot(5,5,i+1)
#     plt.xticks([])
#     plt.yticks([])
#     plt.grid(False)
#     plt.imshow(train_images[i], cmap=plt.cm.binary)
#     plt.xlabel(class_names[train_labels[i]])
# plt.show()


model = keras.Sequential([
    keras.layers.Flatten(input_shape = (28, 28)),
    keras.layers.Dense(100, activation = tf.nn.relu),
    keras.layers.Dense(10, activation = tf.nn.softmax)
])

model.compile(optimizer = tf.train.AdamOptimizer(),
            loss='sparse_categorical_crossentropy',
            metrics = ['accuracy'])

model.fit(train_images, train_labels, epochs = 5)

test_loss, test_acc = model.evaluate(test_images, test_labels)

print('\nTest accuracy:', test_acc)

predictions = model.predict(test_images)
print(predictions[0],np.argmax(predictions[0]),test_labels[0])

img = test_images[0]
print(img.shape)
img = (np.expand_dims(img,0))
print(img.shape)

predictions_single = model.predict(img)
print(predictions_single)