tensorflow1.3 API学习笔记 1

Posted 2022-12-13 刘二毛

tf.layers.conv2d  卷积层

https://www.tensorflow.org/versions/r1.3/api_docs/python/tf/layers/conv2d

conv2d(
    inputs,
    filters,
    kernel_size,
    strides=(1, 1),
    padding='valid',
    data_format='channels_last',
    dilation_rate=(1, 1),
    activation=None,
    use_bias=True,
    kernel_initializer=None,
    bias_initializer=tf.zeros_initializer(),
    kernel_regularizer=None,
    bias_regularizer=None,
    activity_regularizer=None,
    trainable=True,
    name=None,
    reuse=None
)

参数说明：

• inputs: 输入数据.
• filters: 卷积核. 类型和input必须相同，4维tensor, [filter_height, filter_width, in_channels, out_channels],如[5,5,3,32].
• kernel_size: An integer or tuple/list of 2 integers, specifying the height and width of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions.
• strides: An integer or tuple/list of 2 integers, specifying the strides of the convolution along the height and width. Can be a single integer to specify the same value for all spatial dimensions. Specifying any stride value != 1 is incompatible with specifying any dilation_rate value != 1.
• padding: One of "valid" or "same" (case-insensitive).

• data_format: A string, one of channels_last (default) or channels_first. The ordering of the dimensions in the inputs. channels_last corresponds to inputs with shape (batch, height, width, channels) while channels_first corresponds to inputs with shape (batch, channels, height, width).

• dilation_rate: An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any dilation_rate value != 1 is incompatible with specifying any stride value != 1.

• activation: Activation function. Set it to None to maintain a linear activation.
• use_bias: Boolean, whether the layer uses a bias.
• kernel_initializer: An initializer for the convolution kernel.
• bias_initializer: An initializer for the bias vector. If None, no bias will be applied.
• kernel_regularizer: Optional regularizer for the convolution kernel.
• bias_regularizer: Optional regularizer for the bias vector.
• activity_regularizer: Regularizer function for the output.
• trainable: Boolean, if True also add variables to the graph collection GraphKeys.TRAINABLE_VARIABLES (see tf.Variable).
• name: A string, the name of the layer.
• reuse: Boolean, whether to reuse the weights of a previous layer by the same name.

tf.layers.max_pooling2d

https://www.tensorflow.org/versions/r1.3/api_docs/python/tf/layers/max_pooling2d


max_pooling2d(
    inputs,
    pool_size,
    strides,
    padding='valid',
    data_format='channels_last',
    name=None
)

参数说明：

• inputs: 进行池化的数据。
• pool_size: 池化的核大小(pool_height, pool_width)，如[3，3]. 如果长宽相等，也可以直接设置为一个数，如pool_size=3.
• strides: 池化的滑动步长。可以设置为[1,1]这样的两个整数. 也可以直接设置为一个数，如strides=2
• padding: 边缘填充，'same' 和'valid‘选其一。默认为valid
• data_format: 输入数据格式，默认为channels_last ，即 (batch, height, width, channels),也可以设置为channels_first 对应 (batch, channels, height, width).
• name: 层的名字

示例：

pool1=tf.layers.max_pooling2d(inputs=x, pool_size=[2, 2], strides=1)

# tf.layers.average_pooling2d是均值池化
tf.layers.dense 全连接层
https://www.tensorflow.org/versions/r1.3/api_docs/python/tf/layers/dense

dense(
    inputs,
    units,
    activation=None,
    use_bias=True,
    kernel_initializer=None,
    bias_initializer=tf.zeros_initializer(),
    kernel_regularizer=None,
    bias_regularizer=None,
    activity_regularizer=None,
    trainable=True,
    name=None,
    reuse=None
)

• inputs: 输入数据，2维tensor.
• units: 该层的神经单元结点数。
• activation: 激活函数.
• use_bias: Boolean型，是否使用偏置项.
• kernel_initializer: 卷积核的初始化器.
• bias_initializer: 偏置项的初始化器，默认初始化为0.
• kernel_regularizer: 卷积核化的正则化，可选.
• bias_regularizer: 偏置项的正则化，可选.
• activity_regularizer: 输出的正则化函数.
• trainable: Boolean型，表明该层的参数是否参与训练。如果为真则变量加入到图集合中 GraphKeys.TRAINABLE_VARIABLES (see tf.Variable).
• name: 层的名字.
• reuse: Boolean型, 是否重复使用参数.

全连接层执行操作 outputs = activation(inputs.kernel + bias)

如果执行结果不想进行激活操作，则设置activation=None。

例：

#全连接层
dense1 = tf.layers.dense(inputs=pool3, units=512, activation=tf.nn.relu)
dense2= tf.layers.dense(inputs=dense1, units=512, activation=tf.nn.relu)两个全链接