深度学习之 minist 自定义网络

在使用全连接层的时候我们可以使用高级接口直接调用Dense层,那有没有想过自己实现一个Dense层的,下面我们一起实现一个Dense层

这是自己实现的第一个类,自动调用 call 方法,继承 layers.Layer 类,实现 y = wx + b 

	class MyDense(layers.Layer):
	    def __init__(self, inp_dim, outp_dim):  # 这是输入维度 和 输出维度
	        super(MyDense, self).__init__()  # 需要继承父类
	        self.kernel = self.add_variable('w', [inp_dim, outp_dim])
	        self.bias = self.add_variable('b', [outp_dim])
	
	    def call(self, inputs, **kwargs):
	        out = inputs @ self.kernel + self.bias
	        return out

接下来就是实现自己的模型 MyModel, 继承 keras.Model 类, 同样也是需要调用 super 方法

	class MyModel(keras.Model):
	    def __init__(self):
	        super(MyModel, self).__init__()
	        self.fc1 = MyDense(28 * 28, 256)
	        self.fc2 = MyDense(256, 128)
	        self.fc3 = MyDense(128, 64)
	        self.fc4 = MyDense(64, 32)
	        # 因为这个层是用来对 minist 数据集进行训练 所以最后的输出维度是 10
	        self.fc5 = MyDense(32, 10)
	
	    def call(self, inputs, training=None, mask=None):
	        x = self.fc1(inputs)
	        # 中间加入 relu 非线性作为激活函数
	        x = tf.nn.relu(x)
	        x = self.fc2(x)
	        x = tf.nn.relu(x)
	        x = self.fc3(x)
	        x = tf.nn.relu(x)
	        x = self.fc4(x)
	        x = tf.nn.relu(x)
	        x = self.fc5(x)
	        return x

接下来就是数据预处理函数

	def process(x, y):
	    x = tf.cast(x, dtype=tf.float32) / 255.
	    y = tf.cast(y, dtype=tf.int64)
	    x = tf.reshape(x, [28 * 28])
	    y = tf.one_hot(y, depth=10)
	    return x, y

训练数据部分

	# 设置 batch_size 的大小
	batch_size = 128
	# 加载数据集
	(x, y), (x_test, y_test) = datasets.mnist.load_data()
	db = tf.data.Dataset.from_tensor_slices((x, y))
	db = db.map(process).shuffle(1000).batch(batch_size)
	db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))
	db_test = db_test.map(process).batch(batch_size)
	
	# 直接调用模型  模型的层数已经在自定义里面设置了
	net_work = MyModel()
	net_work.compile(
	    optimizer=optimizers.Adam(lr=0.01), # 设置优化器,并设置学习速率
	    loss=tf.losses.CategoricalCrossentropy(from_logits=True), # 定义损失函数
	    metrics=["accuracy"]  # 设置模型评估参数
	)
	# 进行训练
	net_work.fit(db, epochs=5, validation_data=db_test, validation_freq=2)
	# 在测试集上进行验证
	net_work.evaluate(db_test)

全部代码

	import tensorflow as tf
	from tensorflow.keras import optimizers, datasets, Sequential, metrics, layers
	from tensorflow import keras
	
	
	class MyDense(layers.Layer):
	    def __init__(self, inp_dim, outp_dim):
	        super(MyDense, self).__init__()
	        self.kernel = self.add_variable('w', [inp_dim, outp_dim])
	        self.bias = self.add_variable('b', [outp_dim])
	
	    def call(self, inputs, **kwargs):
	        out = inputs @ self.kernel + self.bias
	        return out
	
	
	class MyModel(keras.Model):
	    def __init__(self):
	        super(MyModel, self).__init__()
	        self.fc1 = MyDense(28 * 28, 256)
	        self.fc2 = MyDense(256, 128)
	        self.fc3 = MyDense(128, 64)
	        self.fc4 = MyDense(64, 32)
	        self.fc5 = MyDense(32, 10)
	
	    def call(self, inputs, training=None, mask=None):
	        x = self.fc1(inputs)
	        x = tf.nn.relu(x)
	        x = self.fc2(x)
	        x = tf.nn.relu(x)
	        x = self.fc3(x)
	        x = tf.nn.relu(x)
	        x = self.fc4(x)
	        x = tf.nn.relu(x)
	        x = self.fc5(x)
	        return x
	
	
	def process(x, y):
	    x = tf.cast(x, dtype=tf.float32) / 255.
	    y = tf.cast(y, dtype=tf.int64)
	    x = tf.reshape(x, [28 * 28])
	    y = tf.one_hot(y, depth=10)
	    return x, y
	
	    # x = tf.cast(x, dtype=tf.float32) / 255.
	    # x = tf.reshape(x, [28 * 28])
	    # y = tf.cast(y, dtype=tf.int32)
	    # y = tf.one_hot(y, depth=10)
	    # return x, y
	
	
	batch_size = 128
	(x, y), (x_test, y_test) = datasets.mnist.load_data()
	
	db = tf.data.Dataset.from_tensor_slices((x, y))
	db = db.map(process).shuffle(1000).batch(batch_size)
	
	db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))
	db_test = db_test.map(process).batch(batch_size)
	
	print(x.shape, y.shape)
	
	net_work = MyModel()
	net_work.compile(
	    optimizer=optimizers.Adam(lr=0.01),
	    loss=tf.losses.CategoricalCrossentropy(from_logits=True),
	    # loss=tf.losses.MSE,
	    metrics=["accuracy"]
	)
	
	net_work.fit(db, epochs=5, validation_data=db_test, validation_freq=2)
	
	net_work.evaluate(db_test)