keras.layer.input()

刺骨的言语ヽ痛彻心扉 2022-02-25 09:56 123阅读 0赞

tenserflow建立网络由于先建立静态的graph，所以没有数据，用placeholder来占位好申请内存。

那么keras的layer类其实是一个方便的直接帮你建立深度网络中的layer的类。

该类继承了object，是个基础的类，后续的诸如input\_layer类都会继承与layer

由于model.py中利用这个方法建立网络，所以仔细看一下：他的说明详尽而丰富。

input()这个方法是用来初始化一个keras tensor的，tensor说白了就是个数组。他强大到之通过输入和输出就能建立一个keras模型。shape或者batch shape 必须只能给一个。shape = \[None,None,None\],会创建一个?\*?\*?的三维数组。

下面还举了个例子，a,b,c都是keras的tensor， \`model = Model(input=\[a, b\], output=c)\`

def Input(shape=None, batch_shape=None,
              name=None, dtype=None, sparse=False,
              tensor=None):
        """`Input()` is used to instantiate a Keras tensor.
    
        A Keras tensor is a tensor object from the underlying backend
        (Theano, TensorFlow or CNTK), which we augment with certain
        attributes that allow us to build a Keras model
        just by knowing the inputs and outputs of the model.
    
        For instance, if a, b and c are Keras tensors,
        it becomes possible to do:
        `model = Model(input=[a, b], output=c)`
    
        The added Keras attributes are:
            `_keras_shape`: Integer shape tuple propagated
                via Keras-side shape inference.
            `_keras_history`: Last layer applied to the tensor.
                the entire layer graph is retrievable from that layer,
                recursively.
    
        # Arguments
            shape: A shape tuple (integer), not including the batch size.
                For instance, `shape=(32,)` indicates that the expected input
                will be batches of 32-dimensional vectors.
            batch_shape: A shape tuple (integer), including the batch size.
                For instance, `batch_shape=(10, 32)` indicates that
                the expected input will be batches of 10 32-dimensional vectors.
                `batch_shape=(None, 32)` indicates batches of an arbitrary number
                of 32-dimensional vectors.
            name: An optional name string for the layer.
                Should be unique in a model (do not reuse the same name twice).
                It will be autogenerated if it isn't provided.
            dtype: The data type expected by the input, as a string
                (`float32`, `float64`, `int32`...)
            sparse: A boolean specifying whether the placeholder
                to be created is sparse.
            tensor: Optional existing tensor to wrap into the `Input` layer.
                If set, the layer will not create a placeholder tensor.
    
        # Returns
            A tensor.
    
        # Example
    
        ```python
        # this is a logistic regression in Keras
        x = Input(shape=(32,))
        y = Dense(16, activation='softmax')(x)
        model = Model(x, y)
        ```
        """

tip：我们在model.py中用到了shape这个attribute，

input_image = KL.Input(
                shape=[None, None, config.IMAGE_SHAPE[2]], name="input_image")
            input_image_meta = KL.Input(shape=[config.IMAGE_META_SIZE],
                                        name="input_image_meta")

阅读input()里面的句子逻辑：

可以发现，进入if语句的情况是batch\_shape不为空，并且tensor为空，此时进入if，用assert判断如果shape不为空，那么久会有错误提示，告诉你要么输入shape 要么输入batch\_shape, 还提示你shape不包含batch个数，就是一个batch包含多少张图片。

那么其实如果tensor不空的话，我们可以发现，也会弹出这个提示，但是作者没有写这种题型，感觉有点没有安全感。注意点好了

if not batch_shape and tensor is None:
            assert shape is not None, ('Please provide to Input either a `shape`'
                                       ' or a `batch_shape` argument. Note that '
                                       '`shape` does not include the batch '
                                       'dimension.')

如果单纯的按照规定输入shape，举个例子：只将shape输入为None，也就是说tensor的dimension我都不知道，但我知道这是个向量，你看着办吧。

input_gt_class_ids = KL.Input(
                    shape=[None], name="input_gt_class_ids", dtype=tf.int32)

就会调用Input()函数中的这个判断句式，注意因为shape是个List，所以shape is not None 会返回true。同时有没有输入batch\_shape的话，就会用shape的参数去创造一个batch\_shape.

if shape is not None and not batch_shape:
            batch_shape = (None,) + tuple(shape)

比如如果输入：

shape = (None,)
    batch_shape = (None,)+shape
    batch_shape
    #会得到(None, None)

可以发现，这里要求使用者至少指明你的数据维度，比如图片的话，是三维的，所以shape至少是\[None,None,None\]，而且我认为shape = \[None,1\] 与shape = \[None\]是一样的都会创建一个不知道长度的向量。