tensorflow2.0(二)----卷积神经网络(CNN)

使用Keras实现卷积神经网络

class CNN(tf.keras.Model):
	def __init__(self):
		super().__init__()
		self.conv1 = tf.keras.layers.Conv2D(
			filters = 32,
			kernel_size=[5,5],
			padding = 'same',
			activation = tf.nn.relu)
		self.pool1 = tf.keras.layers.MaxPool2D(pool_size=[2,2],strides=2)
		self.conv2 = tf.keras.layers.Conv2D(
			filters = 64,
			kernel_size=[5,5],
			padding = 'same',
			activation = tf.nn.relu)
		self.pool2 = tf.keras.layers.MaxPool2D(pool_size=[2,2],strides=2)
		self.flatten = tf.keras.layers.Reshape(targe_shape=(7*7*64))
		self.dense1 = tf.keras.layers.Dense(units=1024,activation=tf.nn.relu)
		self.dense2 = tf.keras.layers.Dense(units=10)

	
	def call(self,inputs):
		x = self.conv1(inputs)
		x = self.pool1(x)
		x = self.conv2(x)
		x = self.pool2(x)
		x = self.flatten(x)
		x = self.dense1(x)
		x = self.dense2(x)
		output = tf.nn.softmax(x)
		return output

'''
模型训练：tf.keras.losses 和 tf.keras.optimizer
'''
num_epochs = 5
batch_size = 50
learning_rate = 0.001
model = CNN()
data_loader = MNISTLoader()
optimizer = tf.keras.optimizers.Adam(learning_rate)

num_batches = int(data_loader.num_train_data // batch_size * num_epochs)
for batch_index in range(num_batches):
	x,y = data_loader.get_batch(batch_size)
	with tf.GradieneTape() as tape:
		y_pred = model(x)
		loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=y,y_pred=y_pred)
		print("batch &d:loss %f" % (batch_index.loss.numpy()))
	grads = tape.gradient(loss,model.variables)
	optimizer.apply_gradients(grads_and_vars=zip(grads,model.variables))

'''
模型评估：tf.keras.metrics
'''
sparse_categorical_accuracy = tf.keras.metrics.SparseCategoricalAccuracy()
num_batches = int(data_losder.num_test_data // batch_size)
for batch_index in range(num_batches):
	start_index,end_index = batch_index *batch_size，（batch_index + 1）* batch_size 
	y_pred = model.predict(data_loader.test_data [START_INDEX：END_INDEX])
	sparse_categorical_accuracy.update_state(y_ture = data_loader.test_label[start_index:
	end_index],y_pred=y_pred)
	print("test accuracy: %f" % sparse_categorical_accuracy.result())

使用keras中预定义的经典卷积神经网络结构
tf.keras.application中有一些预定义好的经典卷积神经网络结构，如VGG16、VGG19、ResNet、MobileNet等。下面是用MobileNetV2网络在tf.flowers五分类数据集上进行训练，将weights设置成None，随机初始化变量而不用使用预训练权值。同时classes设置为5，对用5分类数据集。

import tensorflow as tf 
import tensorflow_datasets as tfds

num_batches = 100
batch_size = 50
learning_rate = 0.001

dataset = tfds.load("tf_flowers",split=tfds.Split.TRAIN,as_supervised=True)
dataset = dataset.map(lambda img,label:(tf.image.resize(img,[224,224])/255.0,
	label)).shuffle(1024).batch(32)
model = tf.keras.application.MobileNetV2(weights = None,classes=5)
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
for image,labels in dataset:
	with tf.GradientTape() as tape:
		labels_pred = model(image)
		loss = tf.keras.losses.sparse_categorical_crossentropy(y_ture=labels,y_pred=labels_pred)
		loss = tf.reduce_mean(loss)
		print("loss %f" % loss.numpy())
	grads = tape.gradien(loss,model.trainable_variables)
	optimizer.apply_gradients(grads_and_vars=zip(grads,model.trainable_variables))