Python深度学习入门之mnist-inception（Tensorflow2.0实现）

mnist手写数字数据集深度学习最常用的数据集，本文以mnist数据集为例，利用Tensorflow2.0框架搭建inception网络，实现mnist数据集识别任务，并画出各个曲线。

Demo完整代码如下：

import tensorflow as tf
from tensorflow.keras import layers
import numpy as np

#加载mnist数据集
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
#预处理
x_train, x_test = x_train.astype(np.float32)/255., x_test.astype(np.float32)/255.
x_train, x_test = np.expand_dims(x_train, axis=3), np.expand_dims(x_test, axis=3)
# 创建训练集50000、验证集10000以及测试集10000
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]
#标签转为one-hot格式
y_train = tf.one_hot(y_train, depth=10).numpy()
y_val = tf.one_hot(y_val, depth=10).numpy()
y_test = tf.one_hot(y_test, depth=10).numpy()

# tf.data.Dataset 批处理
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(100).repeat()

val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val)).batch(100).repeat()

test_dataset = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(100).repeat()

from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from tensorflow import keras

class ConvBNRelu(keras.Model):
    def __init__(self, ch, kernelsz=3, strides=1, padding='same'):
        super(ConvBNRelu, self).__init__()
        self.model = keras.models.Sequential([
            keras.layers.Conv2D(ch, kernelsz, strides=strides, padding=padding),
            keras.layers.BatchNormalization(),
            keras.layers.ReLU()
        ])         
    def call(self, x, training=None):
        x = self.model(x, training=training)
        return x 

class InceptionBlk(keras.Model):
    def __init__(self, ch, strides=1):
        super(InceptionBlk, self).__init__()
        self.ch = ch
        self.strides = strides
        self.conv1 = ConvBNRelu(ch, strides=strides)
        self.conv2 = ConvBNRelu(ch, kernelsz=3, strides=strides)
        self.conv3_1 = ConvBNRelu(ch, kernelsz=3, strides=strides)
        self.conv3_2 = ConvBNRelu(ch, kernelsz=3, strides=1)
        self.pool = keras.layers.MaxPooling2D(3, strides=1, padding='same')
        self.pool_conv = ConvBNRelu(ch, strides=strides)
    def call(self, x, training=None):
        x1 = self.conv1(x, training=training)
        x2 = self.conv2(x, training=training)    
        x3_1 = self.conv3_1(x, training=training)
        x3_2 = self.conv3_2(x3_1, training=training)         
        x4 = self.pool(x)
        x4 = self.pool_conv(x4, training=training)
        # concat along axis=channel
        x = tf.concat([x1, x2, x3_2, x4], axis=3)
        return x

class Inception(keras.Model):
    def __init__(self, num_layers, num_classes, init_ch=16, **kwargs):
        super(Inception, self).__init__(**kwargs)
        self.in_channels = init_ch
        self.out_channels = init_ch
        self.num_layers = num_layers
        self.init_ch = init_ch
        self.conv1 = ConvBNRelu(init_ch)
        self.blocks = keras.models.Sequential(name='dynamic-blocks')
        for block_id in range(num_layers):
            for layer_id in range(2):
                if layer_id == 0:
                    block = InceptionBlk(self.out_channels, strides=2)
                else:
                    block = InceptionBlk(self.out_channels, strides=1)
                self.blocks.add(block)
            # enlarger out_channels per block    
            self.out_channels *= 2
        self.avg_pool = keras.layers.GlobalAveragePooling2D()
        self.fc = keras.layers.Dense(num_classes)
    def call(self, x, training=None):
        out = self.conv1(x, training=training)
        out = self.blocks(out, training=training)
        out = self.avg_pool(out)
        out = self.fc(out)
        return out    

#网络参数设置
model_inception = Inception(2, 10)
model_inception.compile(optimizer=keras.optimizers.Adam(0.001),
              loss=keras.losses.CategoricalCrossentropy(from_logits=True),
              metrics=['acc'])
model_inception.build(input_shape=(None, 28, 28, 1))
#打印网络参数
model_inception.summary()

#开始训练
history_inception = model_inception.fit(train_dataset, epochs=50, steps_per_epoch=30, validation_data=val_dataset, validation_steps=3)
#模型评估及保存权重
model_inception.evaluate(test_dataset, steps=100)
model_inception.save_weights('save_model/inception_mnist/inception_mnist_weights.ckpt')

网络参数

评估结果

绘制曲线代码

import matplotlib.pyplot as plt

#输入两个曲线的信息
plt.figure( figsize=(12,8), dpi=80 )
plt.plot(history_inception.epoch, history_inception.history.get('loss'), color='r', label = 'loss')
plt.plot(history_inception.epoch, history_inception.history.get('acc'), color='g', linestyle='-.', label = 'acc')
plt.plot(history_inception.epoch, history_inception.history.get('val_acc'), color='b', linestyle='--', label = 'val_acc')

#显示图例
plt.legend() #默认loc=Best

#添加网格信息
plt.grid(True, linestyle='--', alpha=0.5) #默认是True，风格设置为虚线，alpha为透明度

#添加标题
plt.xlabel('epochs')
plt.ylabel('loss/acc')
plt.title('inception_Curve of loss/acc Change with epochs in Mnist')

plt.savefig('./save_png/inception.png')

plt.show()

网络曲线