当前位置: 首页>>代码示例>>Python>>正文


Python gen_math_ops.not_equal方法代码示例

本文整理汇总了Python中tensorflow.python.ops.gen_math_ops.not_equal方法的典型用法代码示例。如果您正苦于以下问题:Python gen_math_ops.not_equal方法的具体用法?Python gen_math_ops.not_equal怎么用?Python gen_math_ops.not_equal使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在tensorflow.python.ops.gen_math_ops的用法示例。


在下文中一共展示了gen_math_ops.not_equal方法的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: count_nonzero

# 需要导入模块: from tensorflow.python.ops import gen_math_ops [as 别名]
# 或者: from tensorflow.python.ops.gen_math_ops import not_equal [as 别名]
def count_nonzero(input_tensor,
                  axis=None,
                  keep_dims=False,
                  dtype=dtypes.int64,
                  name=None,
                  reduction_indices=None):
  """Computes number of nonzero elements across dimensions of a tensor.

  Reduces `input_tensor` along the dimensions given in `axis`.
  Unless `keep_dims` is true, the rank of the tensor is reduced by 1 for each
  entry in `axis`. If `keep_dims` is true, the reduced dimensions
  are retained with length 1.

  If `axis` has no entries, all dimensions are reduced, and a
  tensor with a single element is returned.

  **NOTE** Floating point comparison to zero is done by exact floating point
  equality check.  Small values are **not** rounded to zero for purposes of
  the nonzero check.

  For example:

  ```python
  # 'x' is [[0, 1, 0]
  #         [1, 1, 0]]
  tf.count_nonzero(x) ==> 3
  tf.count_nonzero(x, 0) ==> [1, 2, 0]
  tf.count_nonzero(x, 1) ==> [1, 2]
  tf.count_nonzero(x, 1, keep_dims=True) ==> [[1], [2]]
  tf.count_nonzero(x, [0, 1]) ==> 3
  ```

  Args:
    input_tensor: The tensor to reduce. Should be of numeric type, or `bool`.
    axis: The dimensions to reduce. If `None` (the default),
      reduces all dimensions.
    keep_dims: If true, retains reduced dimensions with length 1.
    dtype: The output dtype; defaults to `tf.int64`.
    name: A name for the operation (optional).
    reduction_indices: The old (deprecated) name for axis.

  Returns:
    The reduced tensor (number of nonzero values).
  """
  with ops.name_scope(name, "count_nonzero", [input_tensor]):
    input_tensor = ops.convert_to_tensor(input_tensor, name="input_tensor")
    zero = input_tensor.dtype.as_numpy_dtype()
    return cast(
        reduce_sum(
            # int64 reduction happens on GPU
            to_int64(gen_math_ops.not_equal(input_tensor, zero)),
            axis=axis,
            keep_dims=keep_dims,
            reduction_indices=reduction_indices),
        dtype=dtype) 
开发者ID:ryfeus,项目名称:lambda-packs,代码行数:57,代码来源:math_ops.py

示例2: count_nonzero

# 需要导入模块: from tensorflow.python.ops import gen_math_ops [as 别名]
# 或者: from tensorflow.python.ops.gen_math_ops import not_equal [as 别名]
def count_nonzero(input_tensor, reduction_indices=None, keep_dims=False,
                  dtype=dtypes.int64, name=None):
  """Computes number of nonzero elements across dimensions of a tensor.

  Reduces `input_tensor` along the dimensions given in `reduction_indices`.
  Unless `keep_dims` is true, the rank of the tensor is reduced by 1 for each
  entry in `reduction_indices`. If `keep_dims` is true, the reduced dimensions
  are retained with length 1.

  If `reduction_indices` has no entries, all dimensions are reduced, and a
  tensor with a single element is returned.

  **NOTE** Floating point comparison to zero is done by exact floating point
  equality check.  Small values are **not** rounded to zero for purposes of
  the nonzero check.

  For example:

  ```python
  # 'x' is [[0, 1, 0]
  #         [1, 1, 0]]
  tf.count_nonzero(x) ==> 3
  tf.count_nonzero(x, 0) ==> [1, 2, 0]
  tf.count_nonzero(x, 1) ==> [1, 2]
  tf.count_nonzero(x, 1, keep_dims=True) ==> [[1], [2]]
  tf.count_nonzero(x, [0, 1]) ==> 3
  ```

  Args:
    input_tensor: The tensor to reduce. Should be of numeric type, or `bool`.
    reduction_indices: The dimensions to reduce. If `None` (the default),
      reduces all dimensions.
    keep_dims: If true, retains reduced dimensions with length 1.
    dtype: The output dtype; defaults to `tf.int64`.
    name: A name for the operation (optional).

  Returns:
    The reduced tensor (number of nonzero values).
  """
  with ops.name_scope(name, "count_nonzero", [input_tensor]):
    input_tensor = ops.convert_to_tensor(input_tensor, name="input_tensor")
    zero = input_tensor.dtype.as_numpy_dtype()
    return cast(
        reduce_sum(
            # int64 reduction happens on GPU
            to_int64(gen_math_ops.not_equal(input_tensor, zero)),
            reduction_indices=reduction_indices,
            keep_dims=keep_dims),
        dtype=dtype) 
开发者ID:tobegit3hub,项目名称:deep_image_model,代码行数:51,代码来源:math_ops.py

示例3: count_nonzero

# 需要导入模块: from tensorflow.python.ops import gen_math_ops [as 别名]
# 或者: from tensorflow.python.ops.gen_math_ops import not_equal [as 别名]
def count_nonzero(input_tensor,
                  axis=None,
                  keep_dims=False,
                  dtype=dtypes.int64,
                  name=None,
                  reduction_indices=None):
  """Computes number of nonzero elements across dimensions of a tensor.

  Reduces `input_tensor` along the dimensions given in `axis`.
  Unless `keep_dims` is true, the rank of the tensor is reduced by 1 for each
  entry in `axis`. If `keep_dims` is true, the reduced dimensions
  are retained with length 1.

  If `axis` has no entries, all dimensions are reduced, and a
  tensor with a single element is returned.

  **NOTE** Floating point comparison to zero is done by exact floating point
  equality check.  Small values are **not** rounded to zero for purposes of
  the nonzero check.

  For example:

  ```python
  x = tf.constant([[0, 1, 0], [1, 1, 0]])
  tf.count_nonzero(x)  # 3
  tf.count_nonzero(x, 0)  # [1, 2, 0]
  tf.count_nonzero(x, 1)  # [1, 2]
  tf.count_nonzero(x, 1, keep_dims=True)  # [[1], [2]]
  tf.count_nonzero(x, [0, 1])  # 3
  ```

  Args:
    input_tensor: The tensor to reduce. Should be of numeric type, or `bool`.
    axis: The dimensions to reduce. If `None` (the default),
      reduces all dimensions. Must be in the range
      `[-rank(input_tensor), rank(input_tensor))`.
    keep_dims: If true, retains reduced dimensions with length 1.
    dtype: The output dtype; defaults to `tf.int64`.
    name: A name for the operation (optional).
    reduction_indices: The old (deprecated) name for axis.

  Returns:
    The reduced tensor (number of nonzero values).
  """
  with ops.name_scope(name, "count_nonzero", [input_tensor]):
    input_tensor = ops.convert_to_tensor(input_tensor, name="input_tensor")
    zero = input_tensor.dtype.as_numpy_dtype()
    return cast(
        reduce_sum(
            # int64 reduction happens on GPU
            to_int64(gen_math_ops.not_equal(input_tensor, zero)),
            axis=axis,
            keep_dims=keep_dims,
            reduction_indices=reduction_indices),
        dtype=dtype) 
开发者ID:PacktPublishing,项目名称:Serverless-Deep-Learning-with-TensorFlow-and-AWS-Lambda,代码行数:57,代码来源:math_ops.py


注:本文中的tensorflow.python.ops.gen_math_ops.not_equal方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。