fashion_mnist识别的卷积网络实现

import tensorflow as tf
import numpy as np
import pandas as pd
import os
import time
import matplotlib.pyplot as plt

from tensorflow import keras
import sklearn as sk

fashion_mnist = keras.datasets.fashion_mnist
(x_train_all,y_train_all),(x_test,y_test) = fashion_mnist.load_data()
x_valid , x_train = x_train_all[:5000] , x_train_all[5000:]
y_valid , y_train = y_train_all[:5000] , y_train_all[5000:]

from sklearn.preprocessing import StandardScaler
scaler =StandardScaler()
x_train_scaled = scaler.fit_transform(x_train.astype(np.float32).reshape(-1,1)).reshape(-1,28,28,1)
x_valid_scaled = scaler.transform(x_valid.astype(np.float32).reshape(-1,1)).reshape(-1,28,28,1)
x_test_scaled = scaler.transform(x_test.astype(np.float32).reshape(-1,1)).reshape(-1,28,28,1)#在卷积网络中就要将通道数考虑上，这里黑白图像通道数就是1




model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv2D(filters=32,kernel_size=3,strides=1,padding='same',activation='selu',input_shape=(28,28,1)))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Conv2D(filters=32,kernel_size=3,strides=1,padding='same',activation='relu'))

model.add(tf.keras.layers.MaxPool2D(pool_size=2))
model.add(tf.keras.layers.Conv2D(filters=64,kernel_size=3,strides=1,padding='same',activation='selu'))
model.add(tf.keras.layers.Conv2D(filters=64,kernel_size=3,strides=1,padding='same',activation='selu'))
model.add(tf.keras.layers.MaxPool2D(pool_size=2))
model.add(tf.keras.layers.Conv2D(filters=128,kernel_size=3,strides=1,padding='same',activation='selu'))
model.add(tf.keras.layers.Conv2D(filters=128,kernel_size=3,strides=1,padding='same',activation='selu'))
model.add(tf.keras.layers.MaxPool2D(pool_size=2))
model.add(tf.keras.layers.Conv2D(filters=256,kernel_size=3,strides=1,padding='same',activation='selu'))
model.add(tf.keras.layers.Conv2D(filters=256,kernel_size=3,strides=1,padding='same',activation='selu'))
model.add(tf.keras.layers.MaxPool2D(pool_size=2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(256,activation='relu'))
model.add(tf.keras.layers.Dense(64,activation='relu'))
model.add(tf.keras.layers.Dense(10,activation='softmax'))

callbacks=[keras.callbacks.EarlyStopping(patience=1,min_delta=1e-2),
           keras.callbacks.TensorBoard('logs'),
           keras.callbacks.ModelCheckpoint('cnn5.h5')]
model.compile(loss='sparse_categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

weights_path = 'cnn.h5'

model.load_weights(weights_path, by_name=True)

model.summary()

history = model.fit(x_train_scaled,y_train,epochs=1,
                    validation_data=(x_valid_scaled,y_valid),
                    callbacks=callbacks)

def print_train_image(history):
    pd.DataFrame(history.history).plot(figsize=(2,2))
    plt.grid(True)
    plt.gca().set_ylim(0,1)
    plt.gca().set_xlim(0,1)
    plt.show()

print_train_image(history)

model.evaluate(x_test_scaled,y_test)