VGG13_cifa10分类

链接：https://pan.baidu.com/s/1Nxty7ntGSUUA18oa_-ORSQ
提取码：in9m
cifar10数据集百度云链接

从本地加载图片

import os
import numpy as np
import pickle as p

def load_CIFAR_batch(filename):
    with open(filename,'rb')as f:
        data_dict = p.load(f,encoding='bytes')
        images = data_dict[b'data']
        labels =data_dict[b'labels']
        
        images = images.reshape(10000,3,32,32)
        images = images.transpose(0,2,3,1)
        labels = np.array(labels)
        return images,labels

def load_CIFAR_data(data_dir):
    images_train=[]
    labels_train=[]
    for i in range(5):
        f = os.path.join(data_dir,'data_batch_%d'%(i+1))
        print('loading',f)
        images_batch,label_batch = load_CIFAR_batch(f)
        
        images_train.append(images_batch)
        labels_train.append(label_batch)
        
        Xtrain = np.concatenate(images_train)
        Ytrain = np.concatenate(labels_train)
        del images_batch,label_batch
    Xtest,Ytest = load_CIFAR_batch(os.path.join(data_dir,'test_batch'))
    print('finished loadding CIFAR-10 data')
    return Xtrain,Ytrain,Xtest,Ytest
data_dir = 'D:\cat_dog\cifar-10-python\cifar-10-batches-py'
train_images, train_labels, test_images, test_labels = load_CIFAR_data(data_dir)
train_images, test_images = train_images/255, test_images/255

数据集数据类型转换一下

import tensorflow as tf
from tensorflow.keras import layers, optimizers, datasets, Sequential
from tensorflow import keras
#转换之前的类型
train_labels[0].dtype,train_images[0].dtype
#输出(dtype('int32'), dtype('float64'))
#转换为float32的
train_images, test_images = tf.cast(train_images,dtype=tf.float32),tf.cast(test_images,dtype=tf.float32)

VGG13模型

def VGG13_inference(in_shape):
    model = keras.Sequential(name='VGG13')   
    #unit1            
    model.add(layers.Conv2D(64,(3,3),input_shape=(in_shape[1],in_shape[2],in_shape[3]),
                strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform'))  
    model.add(layers.Conv2D(64,(3,3),input_shape=(in_shape[1],in_shape[2],in_shape[3]),
                padding='same',activation='relu',kernel_initializer='uniform'))  
    model.add(layers.MaxPooling2D(pool_size=(2,2),strides=2,padding='same'))  
     #unit2    
    model.add(layers.Conv2D(128,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
    model.add(layers.Conv2D(128,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
    model.add(layers.MaxPooling2D(pool_size=(2,2),strides=2, padding='same'))  
    #unit3  
#     model.add(layers.Conv2D(256,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
#     model.add(layers.Conv2D(256,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
#     model.add(layers.MaxPooling2D(pool_size=(2,2),strides=2, padding='same'))
#     #unit4  
#     model.add(layers.Conv2D(512,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
#     model.add(layers.Conv2D(512,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
#     model.add(layers.MaxPooling2D(pool_size=(2,2),strides=2, padding='same'))
#     #unit5    
#     model.add(layers.Conv2D(512,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
#     model.add(layers.Conv2D(512,(3,3),strides=(1,1),padding='same',activation='relu',kernel_initializer='uniform')) 
#     model.add(layers.MaxPooling2D(pool_size=(2,2),strides=2, padding='same'))
    
    model.add(layers.Flatten())  
    model.add(layers.Dense(256,activation='relu'))  
#     model.add(layers.Dropout(0.5))  
    model.add(layers.Dense(128,activation='relu'))  
#     model.add(layers.Dropout(0.5))  
    model.add(layers.Dense(10,activation='softmax'))  
    
    model.compile(optimizer=keras.optimizers.Adam(),
                loss='sparse_categorical_crossentropy', #不能直接用函数，否则在与测试加载模型不成功！
                metrics=['accuracy'])
    model.summary()  
    return model


x_shape  = train_images.shape
 
VGG13_model = VGG13_inference(x_shape)
totall_epochs = 0
epochs = 10

history = VGG13_model.fit(train_images, train_labels, batch_size=64, epochs=epochs, validation_split=0.3)

plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.legend(['training', 'valivation'], loc='upper left')
plt.show()

res = VGG13_model.evaluate(test_images, test_labels)
print(res)

unit3、4、5被注释掉了，因为实验发现处理cifar10用不了这么深的层，反而准确率会很低很低。



测试集结果

这个网络还是可以滴。