tf.reshape[tensor, [-1, x, y]]源码解析

最新推荐文章于 2023-08-31 23:59:16 发布

独孤岁月

最新推荐文章于 2023-08-31 23:59:16 发布

阅读量279

点赞数

分类专栏：无聊解闷文章标签： python tensorflow

本文链接：https://blog.csdn.net/Z_baihang/article/details/112218598

版权

无聊解闷专栏收录该内容

32 篇文章 4 订阅

订阅专栏

tf.reshape源码解析：
功能：重置向量的大小
使用：shape中的-1表示为默认填充值，在满足其他维度的前提下，剩下的值大小
源码解析如下：

def reshape(tensor, shape, name=None):
  r"""Reshapes a tensor.

  Given `tensor`, this operation returns a tensor that has the same values
  as `tensor` with shape `shape`.

  If one component of `shape` is the special value -1, the size of that dimension
  is computed so that the total size remains constant.  In particular, a `shape`
  of `[-1]` flattens into 1-D.  At most one component of `shape` can be -1.

  If `shape` is 1-D or higher, then the operation returns a tensor with shape
  `shape` filled with the values of `tensor`. In this case, the number of elements
  implied by `shape` must be the same as the number of elements in `tensor`.

  For example:


  # tensor 't' is [1, 2, 3, 4, 5, 6, 7, 8, 9]
  # tensor 't' has shape [9]   向量共9个元素
  
  reshape(t, [3, 3]) ==> [[1, 2, 3],
                          [4, 5, 6],
                          [7, 8, 9]]  # 重置为3x3

  # tensor 't' is [[[1, 1], [2, 2]],
  #                [[3, 3], [4, 4]]]
  # tensor 't' has shape [2, 2, 2]  向量大小为[2,2,2],共8个元素
  reshape(t, [2, 4]) ==> [[1, 1, 2, 2],
                          [3, 3, 4, 4]]  # 重置为2x4

  # tensor 't' is [[[1, 1, 1],
  #                 [2, 2, 2]],
  #                [[3, 3, 3],
  #                 [4, 4, 4]],
  #                [[5, 5, 5],
  #                 [6, 6, 6]]]
  # tensor 't' has shape [3, 2, 3]  共 3x2x3=18个元素
  # pass '[-1]' to flatten 't'   其中的-1相当于默认，这一维度的值自动填充，此处变更为1维。默认填充为18
  reshape(t, [-1]) ==> [1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6]

  # -1 can also be used to infer the shape

  # -1 is inferred to be 9:    -1默认为填充9
  reshape(t, [2, -1]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3],
                           [4, 4, 4, 5, 5, 5, 6, 6, 6]]   # 共18个元素，重置为二维，其中一维大小为2，另一维大小为 18/2=9，所以-1代替9
  # -1 is inferred to be 2: -1默认代替2
  reshape(t, [-1, 9]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3],
                           [4, 4, 4, 5, 5, 5, 6, 6, 6]]  # 共18个元素，重置为二维，其中一维大小为9，另一维大小为 18/9=2，所以-1代替2
  # -1 is inferred to be 3: -1代替3
  reshape(t, [ 2, -1, 3]) ==> [[[1, 1, 1],
                                [2, 2, 2],
                                [3, 3, 3]],
                               [[4, 4, 4],
                                [5, 5, 5],
                                [6, 6, 6]]]   # 共18个元素，重置为三维，其中一维大小为2，另一维大小为3，最后一维的大小为： 18/3/2=3，所以-1代替3

  # tensor 't' is [7]
  # shape `[]` reshapes to a scalar   空也表示为默认填充值
  reshape(t, []) ==> 7