tensorflow对fashion_MNIST数据集训练

导包

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

导入数据集

fashion_mnist = keras.datasets.fashion_mnist

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

归一化

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']

查看示例图片

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()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-AgMAiSak-1609823925870)(output_4_0.png)]

构建神经元

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10,activation='softmax')
])

编译

model.compile(optimizer='adam',
             loss=keras.losses.sparse_categorical_crossentropy,
             metrics=['acc'])

对神经元进行训练

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

Epoch 1/5
1875/1875 [==============================] - 2s 1ms/step - loss: 0.1430 - acc: 0.9467
Epoch 2/5
1875/1875 [==============================] - 2s 1ms/step - loss: 0.1408 - acc: 0.9462
Epoch 3/5
1875/1875 [==============================] - 2s 1ms/step - loss: 0.1357 - acc: 0.9484
Epoch 4/5
1875/1875 [==============================] - 2s 1ms/step - loss: 0.1331 - acc: 0.9499
Epoch 5/5
1875/1875 [==============================] - 2s 1ms/step - loss: 0.1302 - acc: 0.9517

保存预测结果

predictions=model.predict(test_images)

predict_model[0]

array([7.2180695e-10, 1.3308259e-09, 2.8960994e-09, 1.4506558e-09,
       1.7675823e-10, 3.7347601e-04, 3.9232624e-08, 8.0256416e-03,
       1.7582073e-07, 9.9160075e-01], dtype=float32)

np.argmax(predict_model[0])

9

test_labels[0]

9

制图方法

# 第一个参数是顺位、预测分类(数组格式)、真实分类、图片
def plot_image(i, predictions_array, true_label, img):
  # 预测分类、真实分类、图片
    predictions_array, true_label, img = predictions_array, true_label[i], img[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])
      # 展示图片
    plt.imshow(img, cmap=plt.cm.binary)
  # 获取预测结果并判断预测是否正确
    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)
# 绘制预测概率分布图
def plot_value_array(i, predictions_array, true_label):
    predictions_array, true_label = predictions_array, true_label[i]
    plt.grid(False)
    plt.xticks(range(10))
    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')

将预测结果进行展示

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[i], test_labels, test_images)
    plt.subplot(num_rows, 2*num_cols, 2*i+2)
    plot_value_array(i, predictions[i], test_labels)
plt.tight_layout()
plt.show()