tf.layers.conv2d

tf.layers.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,
    kernel_constraint=None,
    bias_constraint=None,
    trainable=True,
    name=None,
    reuse=None
)

Arguments:

• inputs: Tensor input.

• filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution).

• 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, the default initializer will be used.

• kernel_regularizer: Optional regularizer for the convolution kernel.

• bias_regularizer: Optional regularizer for the bias vector.

• activity_regularizer: Optional regularizer function for the output.

• kernel_constraint: Optional projection function to be applied to the kernel after being updated by an Optimizer (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training.

• bias_constraint: Optional projection function to be applied to the bias after being updated by an Optimizer.

• 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.

注意：

• padding的参数默认值为valid,若想使输出图片长宽和输入图片一致，应加上：padding='same' 
• use_bias可设置为False或None,不使用偏置
• activation默认为None,不使用激活函数
• tensorflow 所以函数的data_format有两种格式：默认为channels_last(batch,height,width,channels)和channels_first(batch,channels,height,width)