服饰分类识别

219 阅读4分钟

以下内容是在学习过程中的一些笔记,难免会有错误和纰漏的地方。如果造成任何困扰,很抱歉。

此Tensorflow官方案例是机器学习中的Hello World,将训练一个神经网络模型,对运动鞋和衬衫等服装图像进行分类,通过Tensorflow及KerasAPI对图像分类识别有一个基本认知。

数据准备及处理

首先导入相关的类库和数据集

 # TensorFlow and tf.keras
 import tensorflow as tf
 from tensorflow import keras
 ​
 # Helper libraries
 import numpy as np
 import matplotlib.pyplot as plt
 ​
 # 数据集导入
 fashion_mnist = keras.datasets.fashion_mnist
 (train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

该数据集包含 10 个类别的 70,000 个灰度图像。这些图像以低分辨率(28x28 像素)展示了单件衣物

加载数据集会返回四个 NumPy 数组:

  • train_imagestrain_labels 数组是训练集,即模型用于学习的数据;
  • 测试集test_imagestest_labels 数组会被用来对模型进行测试;

我们针对这些标签进行一个简单的分类

 # 将图像的标签分类
 class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
                'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
标签
0T恤/上衣
1裤子
2套头衫
3连衣裙
4外套
5凉鞋
6衬衫
7运动鞋
8
9短靴
 # 浏览数据集
 print(train_images.shape)
 print(len(train_labels))
 print(train_labels)

预处理数据 此时展示的是图像原始像素大小

 # 预处理数据 此时展示的是图像原始像素大小
 plt.figure()
 plt.imshow(train_images[0])
 plt.colorbar()
 plt.grid(False)
 plt.show()

需要将这些值缩小至0到1之间,然后将其馈送到神经网络模型

 # 将这些值缩小至0到1之间 然后将其馈送到神经网络模型
 train_images = train_images / 255.0
 test_images = test_images / 255.0
 ​
 # 验证数据的格式是否正确
 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()

模型构建及训练

构建神经网络前

  1. 配置模型的层;
  2. 编译模型;
 # 构建模型 -- 设置层
 model = keras.Sequential([
     keras.layers.Flatten(input_shape=(28, 28)),
     keras.layers.Dense(128, activation='relu'),
     keras.layers.Dense(10)
 ])

第一层网络:keras.layers.Flatten,将图像格式从二维数组(28 x 28 像素)转换成一维数组(28 x 28 = 784 像素)。将该层视为图像中未堆叠的像素行并将其排列起来。

第二、三层网络:keras.layers.Dense,两层神经元序列。

 # 编译模型
 model.compile(optimizer='adam',
               loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
               metrics=['accuracy'])
 ​
 # 训练模型
 model.fit(train_images, train_labels, epochs=10)
 ​
 # 评估准确率
 test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)
 print('\n 评估准确率 Test accuracy:', test_acc)

模型预测

通过构建模型实现单图预测

 probability_model = tf.keras.Sequential([model,
                                          tf.keras.layers.Softmax()])
 predictions = probability_model.predict(test_images)
 ​
 # 效果查看
 predictions[0]
 test_labels[0]

注入绘制图像的方法更加直观的展示预测结果

# 图表绘制方法
def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_label, img = predictions_array, 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)


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')


# 验证预测结果1
# i = 1
# plt.figure(figsize=(6, 3))
# plt.subplot(1, 2, 1)
# plot_image(i, predictions[i], test_labels, test_images)
# plt.subplot(1, 2, 2)
# plot_value_array(i, predictions[i], test_labels)
# plt.show()

# 用模型的预测绘制几张图像
# Plot the first X test images, their predicted labels, and the true labels.
# Color correct predictions in blue and incorrect predictions in red.
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()

完整代码

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

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

# 数据集导入 图像与标签 训练集与测试集
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

# 将图像的标签分类
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

# 将这些值缩小至0到1之间 然后将其馈送到神经网络模型
train_images = train_images / 255.0
test_images = test_images / 255.0

# 构建模型 -- 设置层
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10)
])

# 编译模型
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# 训练模型
model.fit(train_images, train_labels, epochs=10)

# 评估准确率
test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)
print('\n 评估准确率 Test accuracy:', test_acc)

# 预测
probability_model = tf.keras.Sequential([model,
                                         tf.keras.layers.Softmax()])
predictions = probability_model.predict(test_images)


# 效果查看
# predictions[0]
# test_labels[0]

# 图表绘制方法
def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_label, img = predictions_array, 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)


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')


# 验证预测结果1
# i = 1
# plt.figure(figsize=(6, 3))
# plt.subplot(1, 2, 1)
# plot_image(i, predictions[i], test_labels, test_images)
# plt.subplot(1, 2, 2)
# plot_value_array(i, predictions[i], test_labels)
# plt.show()

# 用模型的预测绘制几张图像
# Plot the first X test images, their predicted labels, and the true labels.
# Color correct predictions in blue and incorrect predictions in red.
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()

你学会了吗