tf.nn.conv2d、tf.layers.conv2d、tf.contrib.slim.conv2d理解

tf.nn.conv2d、tf.layers.conv2d、tf.contrib.slim.conv2d理解

tf.nn是最基础的层，需要自己定义权重等，如tf.nn.conv2d，tf.nn.max_pool等。

tf.layers，tf.contrib.slim是较为高级的层。

1. tf.nn.conv2d

tf.nn.conv2d(
    input,
    filters,
    strides, 
    padding, 
    data_format='NHWC', 
    dilations=None, name=None)

tf.nn.conv2d参数详解见这里

2. 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=<tensorflow.python.ops.init_ops.Zeros object at 0x000002596A1FD898>, 
    kernel_regularizer=None,
    bias_regularizer=None, 
    activity_regularizer=None, 
    kernel_constraint=None, 
    bias_constraint=None, 
    trainable=True, 
    name=None,
    reuse=None)

tf.layers.con2d参数详解见这里

3. slim.conv2d

slim.conv2d(inputs,
          num_outputs,
          kernel_size,
          stride=1,
          padding='SAME',
          data_format=None,
          rate=1,
          activation_fn=nn.relu,
          normalizer_fn=None,
          normalizer_params=None,
          weights_initializer=initializers.xavier_initializer(),
          weights_regularizer=None,
          biases_initializer=init_ops.zeros_initializer(),
          biases_regularizer=None,
          reuse=None,
          variables_collections=None,
          outputs_collections=None,
          trainable=True,
          scope=None)

slim.layers.conv2d参数详解见这里