Tensorflow2.0学习笔记-cifar10数据集操作

cifar图片数据训练

Cifar10数据集：
提供5万张32 * 32像素点的十分类彩色图片和标签，用于训练。
提供1万张32 * 32像素点的十分类彩色图片和标签，用于训练。
Cifar数据集是三通道的彩色图片所以我们在设置卷积核数量时，要设置正确。卷积核和个数代表着输出特征图的深度，代码如下：

import tensorflow as tf
import os
import numpy as np
from matplotlib import pyplot as plt
from tensorflow.keras.layers import Conv2D, BatchNormalization, Activation, MaxPool2D, Dropout, Flatten, Dense
from tensorflow.keras import Model
# 设置输出参数为全部输出
np.set_printoptions(threshold=np.inf)
# 读取cifar10数据集
cifar10 = tf.keras.datasets.cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0  # 参数归一化


# 设置对应model.sequential
class Baseline(Model):
    def __init__(self):
        super(Baseline, self).__init__()
        self.c1 = Conv2D(filters=6, kernel_size=(5, 5), padding='same')  # 卷积层
        self.b1 = BatchNormalization()  # BN层
        self.a1 = Activation('relu')  # 激活层
        self.p1 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')  # 池化层
        self.d1 = Dropout(0.2)  # dropout层

        self.flatten = Flatten()
        self.f1 = Dense(128, activation='relu')
        self.d2 = Dropout(0.2)
        self.f2 = Dense(10, activation='softmax')

    def call(self, x):
        x = self.c1(x)
        x = self.b1(x)
        x = self.a1(x)
        x = self.p1(x)
        x = self.d1(x)

        x = self.flatten(x)
        x = self.f1(x)
        x = self.d2(x)
        y = self.f2(x)
        return y


model = Baseline()

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "./checkpoint/Baseline.ckpt"
if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True)

history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1,
                    callbacks=[cp_callback])  # 使用回调函数，实现断点续训
model.summary()

# print(model.trainable_variables)
file = open('./weights.txt', 'w')
for v in model.trainable_variables:
    file.write(str(v.name) + '\n')
    file.write(str(v.shape) + '\n')
    file.write(str(v.numpy()) + '\n')
file.close()

输出结果如下图所示：

Model: "baseline"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              multiple                  456       
_________________________________________________________________
batch_normalization (BatchNo multiple                  24        
_________________________________________________________________
activation (Activation)      multiple                  0         
_________________________________________________________________
max_pooling2d (MaxPooling2D) multiple                  0         
_________________________________________________________________
dropout (Dropout)            multiple                  0         
_________________________________________________________________
flatten (Flatten)            multiple                  0         
_________________________________________________________________
dense (Dense)                multiple                  196736    
_________________________________________________________________
dropout_1 (Dropout)          multiple                  0         
_________________________________________________________________
dense_1 (Dense)              multiple                  1290      
=================================================================
Total params: 198,506
Trainable params: 198,494
Non-trainable params: 12
_________________________________________________________________

在生成的txt文件中，有着训练中用到的参数，参数的总数相加则为输出的参数。如下：

baseline/conv2d/kernel:0 　　　　　　　　(5, 5, 3, 6) # 5*5*3的卷积核一共6个
baseline/conv2d/bias:0                　(6,)         # 卷积核的偏置=卷积核的个数
baseline/batch_normalization/gamma:0　　(6,)         # 批标准化所用到的参数gamma和beta
baseline/batch_normalization/beta:0     (6,)         
baseline/dense/kernel:0                 (1536, 128)  # 卷积全零填充后，输入出的仍然是32*32*6的特征图
                                                     # 再经过池化后，得到的是16*16*6的特征图，对应的数字为1536
baseline/dense/bias:0                   (128,)     
baseline/dense_1/kernel:0               (128, 10)
baseline/dense_1/bias:0                 (10,)