MNIST手写数字识别——03 softmax回归模型

加载 MNIST 数据集

import tensorflow as tf

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

print(x_train.shape, type(x_train))
print(y_train.shape, type(y_train))

1.数据处理：规范化

# 将图像本身从[28,28]转换为[784,]
X_train = x_train.reshape(60000, 784)
X_test = x_test.reshape(10000, 784)
print(X_train.shape, type(X_train))
print(X_test.shape, type(X_test))

# 将数据类型转换为float32
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
# 数据归一化
X_train /= 255
X_test /= 255

2.统计训练数据中各标签数量

import numpy as np
import matplotlib.pyplot as plt

label, count = np.unique(y_train, return_counts=True)
print(label, count)

fig = plt.figure()
plt.bar(label, count, width = 0.7, align='center')
plt.title("Label Distribution")
plt.xlabel("Label")
plt.ylabel("Count")
plt.xticks(label)
plt.ylim(0,7500)

for a,b in zip(label, count):
    plt.text(a, b, '%d' % b, ha='center', va='bottom',fontsize=10)

plt.show()

3.数据处理：one-hot 编码

几种编码方式的对比

Binary	Gray code	One-hot
000	000	00000001
001	001	00000010
010	011	00000100
011	010	00001000
100	110	00010000
101	111	00100000
110	101	01000000
111	100	10000000

one-hot 应用（独热编码）

n_classes = 10
print("Shape before one-hot encoding: ", y_train.shape)
Y_train = tf.keras.utils.to_categorical(y_train, n_classes)
print("Shape after one-hot encoding: ", Y_train.shape)
Y_test = tf.keras.utils.to_categorical(y_test, n_classes)

print(y_train[0])
print(Y_train[0])

4. 使用 Keras sequential model 定义神经网络

Softmax回归：只通过一层简单的以softmax为**函数的全连接层，就可以得到分类的结果。

Sequential = tf.keras.models.Sequential
Dense = tf.keras.layers.Dense
Activation = tf.keras.layers.Activation

# Sequential 序贯模型
# 使用.add()方法将各层添加到模型中：
model = Sequential()
model.add(Dense(10))
model.add(Activation('softmax'))

编译模型

model.compile()

compile(optimizer, loss=None, metrics=None, loss_weights=None, sample_weight_mode=None, weighted_metrics=None, target_tensors=None)

model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')

训练模型，并将指标保存到 history 中

model.fit()

fit(x=None, y=None, batch_size=None, epochs=1, verbose=1, callbacks=None, validation_split=0.0, validation_data=None, shuffle=True, class_weight=None, sample_weight=None, initial_epoch=0, steps_per_epoch=None, validation_steps=None)

history = model.fit(X_train,
                    Y_train,
                    batch_size=128,
                    epochs=10,
                    verbose=2, # 日志输出的复杂度
                    validation_data=(X_test, Y_test))

print(history.history)

loss：训练集损失值

accuracy:训练集准确率

val_loss:测试集损失值

val_accruacy:测试集准确率

可视化指标

fig = plt.figure()
plt.subplot(2, 1, 1)
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('Model Accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='lower right')

plt.subplot(2, 1, 2)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model Loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper right')
plt.tight_layout()

plt.show()

以下5种情况可供参考：

train loss 不断下降，test loss不断下降，说明网络仍在学习;（最好的）

train loss 不断下降，test loss趋于不变，说明网络过拟合;（max pool或者正则化）

train loss 趋于不变，test loss不断下降，说明数据集100%有问题;（检查dataset）

train loss 趋于不变，test loss趋于不变，说明学习遇到瓶颈，需要减小学习率或批量数目;

train loss 不断上升，test loss不断上升，说明网络结构设计不当，训练超参数设置不当，数据集经过清洗等问题。（最不好的情况）

保存模型

model.save()

You can use model.save(filepath) to save a Keras model into a single HDF5 file which will contain:

• the architecture of the model, allowing to re-create the model
• the weights of the model
• the training configuration (loss, optimizer)
• the state of the optimizer, allowing to resume training exactly where you left off.

tf.io.gfile

You can then use keras.models.load_model(filepath) to reinstantiate your model. load_model will also take care of compiling the model using the saved training configuration (unless the model was never compiled in the first place).

import os

gfile = tf.io.gfile

save_dir = "./mnist/softmax-model/"

if gfile.exists(save_dir):
    gfile.rmtree(save_dir)
gfile.mkdir(save_dir)

model_name = 'keras_mnist.h5'
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)

加载模型

mnist_model = tf.keras.models.load_model(model_path)

统计模型在测试集上的分类结果

loss_and_metrics = mnist_model.evaluate(X_test, Y_test, verbose=2)
    
print("Test Loss: {}".format(loss_and_metrics[0]))
print("Test Accuracy: {}%".format(loss_and_metrics[1]*100))

predicted_classes = mnist_model.predict_classes(X_test)

correct_indices = np.nonzero(predicted_classes == y_test)[0]
incorrect_indices = np.nonzero(predicted_classes != y_test)[0]
print("Classified correctly count: {}".format(len(correct_indices)))
print("Classified incorrectly count: {}".format(len(incorrect_indices)))