tensorflow之API函数１

１. tf.nn.conv2d

tf.nn.conv2d(
    input,
    filter,
    strides,
    padding,
    use_cudnn_on_gpu=True,
    data_format='NHWC',
    dilations=[1, 1, 1, 1],
    name=None
)

• input: 指需要做卷积的输入图像，它要求是一个Tensor，具有[batch, in_height, in_width, in_channels]这样的shape，具体含义是[训练时一个batch的图片数量, 图片高度, 图片宽度, 图像通道数]，注意这是一个4维的Tensor，要求类型为float32和float64其中之一
• filter:相当于CNN中的卷积核，它要求是一个Tensor，具有[filter_height, filter_width, in_channels, out_channels]这样的shape，具体含义是[卷积核的高度，卷积核的宽度，图像通道数，卷积核个数]，要求类型与参数input相同，有一个地方需要注意，第三维in_channels，就是参数input的第四维
• strides:卷积时在图像每一维的步长，这是一个一维的向量，长度4
• padding:string类型的量，只能是"SAME","VALID"其中之一，这个值决定了不同的卷积方式
• use_cudnn_on_gpu:bool类型，是否使用cudnn加速，默认为true

结果返回一个Tensor，这个输出，就是我们常说的feature map，shape仍然是[batch, height, width, channels]这种形式。

 

２. tf.nn.max_pool

tf.nn.max_pool(
    value,
    ksize,
    strides,
    padding,
    data_format='NHWC',
    name=None
)

•  value：需要池化的输入，一般池化层接在卷积层后面，所以输入通常是feature map，依然是[batch, height, width, channels]这样的shape
• ksize：池化窗口的大小，取一个四维向量，一般是[1, height, width, 1]，因为我们不想在batch和channels上做池化，所以这两个维度设为了1
• strides：和卷积类似，窗口在每一个维度上滑动的步长，一般也是[1, stride,stride, 1]
• padding：和卷积类似，可以取'VALID' 或者'SAME'

返回一个Tensor，类型不变，shape仍然是[batch, height, width, channels]这种形式

 

３.tf.nn.relu(Z1)

tf.nn.relu(
    features,
    name=None
)

• features: A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64, qint8.
• name: A name for the operation (optional).

tf.nn.relu()函数是将大于0的数保持不变，小于0的数置为0

Returns:

A Tensor. Has the same type as features.

 

４．tf.contrib.layers.flatten(P)

tf.contrib.layers.flatten(
    inputs,
    outputs_collections=None,
    scope=None
)

 

Flattens the input while maintaining the batch_size.

Assumes that the first dimension represents the batch.

• inputs: A tensor of size [batch_size, ...].
• outputs_collections: Collection to add the outputs.
• scope: Optional scope for name_scope.

Returns:

A flattened tensor with shape [batch_size, k].

给定一个输入P，此函数将会把每个样本转化成一维的向量，然后返回一个tensor变量，其维度为（batch_size,k）

 把P保留第一个维度，把第一个维度包含的每一子张量展开成一个行向量，返回张量是一个二维的， shape=（batch_size，….）,一般用于卷积神经网络全链接层前的预处理 

 

５．tf.contrib.layers.fully_connected

tf.contrib.layers.fully_connected(
    inputs,
    num_outputs,
    activation_fn=tf.nn.relu,
    normalizer_fn=None,
    normalizer_params=None,
    weights_initializer=initializers.xavier_initializer(),
    weights_regularizer=None,
    biases_initializer=tf.zeros_initializer(),
    biases_regularizer=None,
    reuse=None,
    variables_collections=None,
    outputs_collections=None,
    trainable=True,
    scope=None
)

 

Adds a fully connected layer.

fully_connected creates a variable called weights, representing a fully connected weight matrix, which is multiplied by the inputs to produce a Tensor of hidden units. If a normalizer_fn is provided (such as batch_norm), it is then applied. Otherwise, if normalizer_fn is None and a biases_initializer is provided then a biases variable would be created and added the hidden units. Finally, if activation_fn is not None, it is applied to the hidden units as well.

• inputs: A tensor of at least rank 2 and static value for the last dimension; i.e. [batch_size, depth], [None, None, None, channels]
• num_outputs: Integer or long, the number of output units in the layer.
• activation_fn: Activation function. The default value is a ReLU function. Explicitly set it to None to skip it and maintain a linear activation.
• normalizer_fn: Normalization function to use instead of biases. If normalizer_fn is provided then biases_initializer and biases_regularizer are ignored and biases are not created nor added. default set to None for no normalizer function
• normalizer_params: Normalization function parameters.
• weights_initializer: An initializer for the weights.
• weights_regularizer: Optional regularizer for the weights.
• biases_initializer: An initializer for the biases. If None skip biases.
• biases_regularizer: Optional regularizer for the biases.
• reuse: Whether or not the layer and its variables should be reused. To be able to reuse the layer scope must be given.
• variables_collections: Optional list of collections for all the variables or a dictionary containing a different list of collections per variable.
• outputs_collections: Collection to add the outputs.
• trainable: If True also add variables to the graph collectionGraphKeys.TRAINABLE_VARIABLES (see tf.Variable).
• scope: Optional scope for variable_scope.

Returns:

The tensor variable representing the result of the series of operations.