tensorflow一、基本分类（出现的问题）

本文例子来自官网：https://tensorflow.google.cn/tutorials/keras/basic_classification

第一步：导入库

# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras

# Helper libraries
import numpy as np
import matplotlib.pyplot as plt

第二步：下载数据集

fashion_mnist = keras.datasets.fashion_mnist

(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

在这步我出现了 1、连接超时的问题。2、EOFError: Compressed file ended before the end-of-stream marker was reached。
出现第一个问题是网络的原因，第二个问题一般这种问题都是因为所下载文件已经存在或下载了部分，若再重新下载，这会出现上述错误。所以你要找到系统默认下载的目录，把里面下好的文件删了
然后去https://github.com/zalandoresearch/fashion-mnist下载训练数据。下载好后放在

下面是所有代码：

# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras

# Helper libraries
import numpy as np
import matplotlib.pyplot as plt

fashion_mnist = keras.datasets.fashion_mnist
#读取数据
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
#归一化
train_images = train_images / 255.0
test_images = test_images / 255.0
#图像显示
# 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(128,activation=tf.nn.relu),
    keras.layers.Dense(10,activation=tf.nn.softmax)
])

model.compile(optimizer=tf.train.AdamOptimizer(),
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
#训练
model.fit(train_images, train_labels, epochs=5)

#对每个测试数据进行预测
predictions = model.predict(test_images)
#绘制物体图片和其下标
def plot_image(i, predictions_array, true_label, img):
  predictions_array, true_label, img = predictions_array[i], true_label[i], img[i]
  plt.grid(False)
  plt.xticks([])
  plt.yticks([])

  plt.imshow(img, cmap=plt.cm.binary)

  predicted_label = np.argmax(predictions_array)
  if predicted_label == true_label:
    color = 'blue'
  else:
    color = 'red'

  plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
                                100*np.max(predictions_array),
                                class_names[true_label]),
                                color=color)
#绘制直方图
def plot_value_array(i, predictions_array, true_label):
  predictions_array, true_label = predictions_array[i], true_label[i]
  plt.grid(False)
  plt.xticks([])
  plt.yticks([])
  thisplot = plt.bar(range(10), predictions_array, color="#777777")
  plt.ylim([0, 1])
  predicted_label = np.argmax(predictions_array)

  thisplot[predicted_label].set_color('red')
  thisplot[true_label].set_color('blue')

# Plot the first X test images, their predicted label, and the true label
# Color correct predictions in blue, incorrect predictions in red
#绘制5*3个物体的预测结果
num_rows = 5
num_cols = 3
num_images = num_rows*num_cols
plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_images):
  plt.subplot(num_rows, 2*num_cols, 2*i+1)
  plot_image(i, predictions, test_labels, test_images)
  plt.subplot(num_rows, 2*num_cols, 2*i+2)
  plot_value_array(i, predictions, test_labels)
plt.show()

这是我测试的结果（居然全对emmmmmmmmmmmm）