如何阅读tensorflow非极大值抑制法源码?

How to read tensorflow non-maximum-suppression method source code?

我正在尝试阅读此line中Tensorflow非最大抑制方法的源代码。它是从 gen_image_ops 文件导入的,但我在 tensorflow 源代码中的任何地方都找不到该文件。

是否有任何来源可以获取此方法的代码?

我也尝试过挖掘他们的回购协议,但没有成功,所以我最终只是从我的编辑那里得到了代码。

我用过 PyCharm 所以我只是 from tensorflow.python.ops.gen_image_ops 然后点击它来获取代码。

我已经添加了它的两个版本,现在就开始吧。

第一个版本

def _non_max_suppression(boxes, scores, max_output_size, iou_threshold=0.5, name=None):
  r"""Greedily selects a subset of bounding boxes in descending order of score,

  pruning away boxes that have high intersection-over-union (IOU) overlap
  with previously selected boxes.  Bounding boxes are supplied as
  [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any
  diagonal pair of box corners and the coordinates can be provided as normalized
  (i.e., lying in the interval [0, 1]) or absolute.  Note that this algorithm
  is agnostic to where the origin is in the coordinate system.  Note that this
  algorithm is invariant to orthogonal transformations and translations
  of the coordinate system; thus translating or reflections of the coordinate
  system result in the same boxes being selected by the algorithm.
  The output of this operation is a set of integers indexing into the input
  collection of bounding boxes representing the selected boxes.  The bounding
  box coordinates corresponding to the selected indices can then be obtained
  using the `tf.gather operation`.  For example:
    selected_indices = tf.image.non_max_suppression(
        boxes, scores, max_output_size, iou_threshold)
    selected_boxes = tf.gather(boxes, selected_indices)

  Args:
    boxes: A `Tensor` of type `float32`.
      A 2-D float tensor of shape `[num_boxes, 4]`.
    scores: A `Tensor` of type `float32`.
      A 1-D float tensor of shape `[num_boxes]` representing a single
      score corresponding to each box (each row of boxes).
    max_output_size: A `Tensor` of type `int32`.
      A scalar integer tensor representing the maximum number of
      boxes to be selected by non max suppression.
    iou_threshold: An optional `float`. Defaults to `0.5`.
      A float representing the threshold for deciding whether boxes
      overlap too much with respect to IOU.
    name: A name for the operation (optional).

  Returns:
    A `Tensor` of type `int32`.
    A 1-D integer tensor of shape `[M]` representing the selected
    indices from the boxes tensor, where `M <= max_output_size`.
  """
  if iou_threshold is None:
    iou_threshold = 0.5
  iou_threshold = _execute.make_float(iou_threshold, "iou_threshold")
  _ctx = _context.context()
  if _ctx.in_graph_mode():
    _, _, _op = _op_def_lib._apply_op_helper(
        "NonMaxSuppression", boxes=boxes, scores=scores,
        max_output_size=max_output_size, iou_threshold=iou_threshold,
        name=name)
    _result = _op.outputs[:]
    _inputs_flat = _op.inputs
    _attrs = ("iou_threshold", _op.get_attr("iou_threshold"))
  else:
    boxes = _ops.convert_to_tensor(boxes, _dtypes.float32)
    scores = _ops.convert_to_tensor(scores, _dtypes.float32)
    max_output_size = _ops.convert_to_tensor(max_output_size, _dtypes.int32)
    _inputs_flat = [boxes, scores, max_output_size]
    _attrs = ("iou_threshold", iou_threshold)
    _result = _execute.execute(b"NonMaxSuppression", 1, inputs=_inputs_flat,
                               attrs=_attrs, ctx=_ctx, name=name)
  _execute.record_gradient(
      "NonMaxSuppression", _inputs_flat, _attrs, _result, name)
  _result, = _result
  return _result

第二个版本

def _non_max_suppression_v2(boxes, scores, max_output_size, iou_threshold, name=None):
  r"""Greedily selects a subset of bounding boxes in descending order of score,

  pruning away boxes that have high intersection-over-union (IOU) overlap
  with previously selected boxes.  Bounding boxes are supplied as
  [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any
  diagonal pair of box corners and the coordinates can be provided as normalized
  (i.e., lying in the interval [0, 1]) or absolute.  Note that this algorithm
  is agnostic to where the origin is in the coordinate system.  Note that this
  algorithm is invariant to orthogonal transformations and translations
  of the coordinate system; thus translating or reflections of the coordinate
  system result in the same boxes being selected by the algorithm.

  The output of this operation is a set of integers indexing into the input
  collection of bounding boxes representing the selected boxes.  The bounding
  box coordinates corresponding to the selected indices can then be obtained
  using the `tf.gather operation`.  For example:

    selected_indices = tf.image.non_max_suppression_v2(
        boxes, scores, max_output_size, iou_threshold)
    selected_boxes = tf.gather(boxes, selected_indices)

  Args:
    boxes: A `Tensor` of type `float32`.
      A 2-D float tensor of shape `[num_boxes, 4]`.
    scores: A `Tensor` of type `float32`.
      A 1-D float tensor of shape `[num_boxes]` representing a single
      score corresponding to each box (each row of boxes).
    max_output_size: A `Tensor` of type `int32`.
      A scalar integer tensor representing the maximum number of
      boxes to be selected by non max suppression.
    iou_threshold: A `Tensor` of type `float32`.
      A 0-D float tensor representing the threshold for deciding whether
      boxes overlap too much with respect to IOU.
    name: A name for the operation (optional).

  Returns:
    A `Tensor` of type `int32`.
    A 1-D integer tensor of shape `[M]` representing the selected
    indices from the boxes tensor, where `M <= max_output_size`.
  """
  _ctx = _context.context()
  if _ctx.in_graph_mode():
    _, _, _op = _op_def_lib._apply_op_helper(
        "NonMaxSuppressionV2", boxes=boxes, scores=scores,
        max_output_size=max_output_size, iou_threshold=iou_threshold,
        name=name)
    _result = _op.outputs[:]
    _inputs_flat = _op.inputs
    _attrs = None
  else:
    boxes = _ops.convert_to_tensor(boxes, _dtypes.float32)
    scores = _ops.convert_to_tensor(scores, _dtypes.float32)
    max_output_size = _ops.convert_to_tensor(max_output_size, _dtypes.int32)
    iou_threshold = _ops.convert_to_tensor(iou_threshold, _dtypes.float32)
    _inputs_flat = [boxes, scores, max_output_size, iou_threshold]
    _attrs = None
    _result = _execute.execute(b"NonMaxSuppressionV2", 1, inputs=_inputs_flat,
                               attrs=_attrs, ctx=_ctx, name=name)
  _execute.record_gradient(
      "NonMaxSuppressionV2", _inputs_flat, _attrs, _result, name)
  _result, = _result
  return _result

Here you go

只要您在他们的 python 操作定义中看到 "import gen_*" 行,他们就会导入一个自动生成的 python 模块,该模块绑定到操作的 C++ 实现。如果您从源代码构建,生成将在那时发生。如果您正在下载 pip 模块或其他一些预构建版本,则生成已经完成,您只是在引用已编译的库。