tf.stack,tf.argmax,SparseCategoricalCrossentropy: loss_object

最新推荐文章于 2022-03-24 22:34:38 发布

csdnhuizhu

最新推荐文章于 2022-03-24 22:34:38 发布

阅读量254

点赞数

CC 4.0 BY-SA版权

分类专栏： # tensorflow

本文链接：https://blog.youkuaiyun.com/csdnhuizhu/article/details/106728605

tensorflow 专栏收录该内容

31 篇文章

订阅专栏

本文深入探讨了TensorFlow中的tf.stack函数，用于将多个张量沿着指定轴堆叠；tf.argmax，用于获取一维张量中最大值的索引；以及SparseCategoricalCrossentropy损失函数，它是训练分类模型时常用的一种损失计算方式。通过实例解析，帮助读者掌握这些关键API的用法。

def stack(values, axis=0, name="stack"):
  """Stacks a list of rank-`R` tensors into one rank-`(R+1)` tensor.
  
  See also `tf.concat`, `tf.tile`, `tf.repeat`.

  Packs the list of tensors in `values` into a tensor with rank one higher than
  each tensor in `values`, by packing them along the `axis` dimension.
  Given a list of length `N` of tensors of shape `(A, B, C)`;

  if `axis == 0` then the `output` tensor will have the shape `(N, A, B, C)`.
  if `axis == 1` then the `output` tensor will have the shape `(A, N, B, C)`.
  Etc.

  For example:

  >>> x = tf.constant([1, 4])
  >>> y = tf.constant([2, 5])
  >>> z = tf.constant([3, 6])
  >>> tf.stack([x, y, z])
  <tf.Tensor: shape=(3, 2), dtype=int32, numpy=
  array([[1, 4],
         [2, 5],
         [3, 6]], dtype=int32)>
  >>> tf.stack([x, y, z], axis=1)
  <tf.Tensor: shape=(2, 3), dtype=int32, numpy=
  array([[1, 2, 3],
         [4, 5, 6]], dtype=int32)>

  This is the opposite of unstack.  The numpy equivalent is `np.stack`

  >>> np.array_equal(np.stack([x, y, z]), tf.stack([x, y, z]))
  True

  Args:
    values: A list of `Tensor` objects with the same shape and type.
    axis: An `int`. The axis to stack along. Defaults to the first dimension.
      Negative values wrap around, so the valid range is `[-(R+1), R+1)`.
    name: A name for this operation (optional).

  Returns:
    output: A stacked `Tensor` with the same type as `values`.

  Raises:
    Va

def argmax_v2(input, axis=None, output_type=dtypes.int64, name=None):
  """Returns the index with the largest value across axes of a tensor.

  Note that in case of ties the identity of the return value is not guaranteed.

  For example:

  >>> A = tf.constant([2, 20, 30, 3, 6])
  >>> tf.math.argmax(A)  # A[2] is maximum in tensor A
  <tf.Tensor: shape=(), dtype=int64, numpy=2>
  >>> B = tf.constant([[2, 20, 30, 3, 6], [3, 11, 16, 1, 8],
  ...                  [14, 45, 23, 5, 27]])
  >>> tf.math.argmax(B, 0)
  <tf.Tensor: shape=(5,), dtype=int64, numpy=array([2, 2, 0, 2, 2])>
  >>> tf.math.argmax(B, 1)
  <tf.Tensor: shape=(3,), dtype=int64, numpy=array([2, 2, 1])>

  Args:
    input: A `Tensor`.
    axis: An integer, the axis to reduce across. Default to 0.
    output_type: An optional output dtype (`tf.int32` or `tf.int64`). Defaults
      to `tf.int64`.
    name: An optional name for the operation.

  Returns:
    A `Tensor` of type `output_type`.

SparseCategoricalCrossentropy: loss_object(y_true, y_pred, sample_weight=None)

Computes the crossentropy loss between the labels and predictions.

Use this crossentropy loss function when there are two or more label classes. We expect labels to be provided as integers. If you want to provide labels using one-hot representation, please use CategoricalCrossentropy loss. There should be \# classes floating point values per feature for y_pred and a single floating point value per feature for y_true.

In the snippet below, there is a single floating point value per example for y_true and \# classes floating pointing values per example for y_pred. The shape of y_true is [batch_size] and the shape of y_pred is [batch_size, num_classes].

Usage:

y_true = [1, 2] y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]] # Using 'auto'/'sum_over_batch_size' reduction type. scce = tf.keras.losses.SparseCategoricalCrossentropy() scce(y_true, y_pred).numpy()