Finally BboxInsideWeights and BboxOutsideWeights are used to specify whether it would contribute to training loss.
Args:
rpn_rois(Variable): A 2-D LoDTensor with shape [N, 4]. N is the number of the GenerateProposalOp's output, each element is a bounding box with [xmin, ymin, xmax, ymax] format.
gt_classes(Variable): A 2-D LoDTensor with shape [M, 1]. M is the number of groundtruth, each element is a class label of groundtruth.
is_crowd(Variable): A 2-D LoDTensor with shape [M, 1]. M is the number of groundtruth, each element is a flag indicates whether a groundtruth is crowd.
rpn_rois(Variable): A 2-D LoDTensor with shape [N, 4]. N is the number of the GenerateProposalOp's output, each element is a bounding box with [xmin, ymin, xmax, ymax] format. The data type can be float32 or float64.
gt_classes(Variable): A 2-D LoDTensor with shape [M, 1]. M is the number of groundtruth, each element is a class label of groundtruth. The data type must be int32.
is_crowd(Variable): A 2-D LoDTensor with shape [M, 1]. M is the number of groundtruth, each element is a flag indicates whether a groundtruth is crowd. The data type must be int32.
gt_boxes(Variable): A 2-D LoDTensor with shape [M, 4]. M is the number of groundtruth, each element is a bounding box with [xmin, ymin, xmax, ymax] format.
im_info(Variable): A 2-D LoDTensor with shape [B, 3]. B is the number of input images, each element consists of im_height, im_width, im_scale.
batch_size_per_im(int): Batch size of rois per images.
fg_fraction(float): Foreground fraction in total batch_size_per_im.
fg_thresh(float): Overlap threshold which is used to chose foreground sample.
bg_thresh_hi(float): Overlap threshold upper bound which is used to chose background sample.
bg_thresh_lo(float): Overlap threshold lower bound which is used to chose background sample.
batch_size_per_im(int): Batch size of rois per images. The data type must be int32.
fg_fraction(float): Foreground fraction in total batch_size_per_im. The data type must be float32.
fg_thresh(float): Overlap threshold which is used to chose foreground sample. The data type must be float32.
bg_thresh_hi(float): Overlap threshold upper bound which is used to chose background sample. The data type must be float32.
bg_thresh_lo(float): Overlap threshold lower bound which is used to chose background sample. The data type must be float32.
bbox_reg_weights(list|tuple): Box regression weights. The data type must be float32.
class_nums(int): Class number. The data type must be int32.
use_random(bool): Use random sampling to choose foreground and background boxes.
is_cls_agnostic(bool): bbox regression use class agnostic simply which only represent fg and bg boxes.
is_cascade_rcnn(bool): it will filter some bbox crossing the image's boundary when setting True.
Returns:
tuple:
A tuple with format``(rois, labels_int32, bbox_targets, bbox_inside_weights, bbox_outside_weights)``.
- **rois**: 2-D LoDTensor with shape ``[batch_size_per_im * batch_size, 4]``. The data type is the same as ``rpn_rois``.
- **labels_int32**: 2-D LoDTensor with shape ``[batch_size_per_im * batch_size, 1]``. The data type must be int32.
- **bbox_targets**: 2-D LoDTensor with shape ``[batch_size_per_im * batch_size, 4 * class_num]``. The regression targets of all RoIs. The data type is the same as ``rpn_rois``.
- **bbox_inside_weights**: 2-D LoDTensor with shape ``[batch_size_per_im * batch_size, 4 * class_num]``. The weights of foreground boxes' regression loss. The data type is the same as ``rpn_rois``.
- **bbox_outside_weights**: 2-D LoDTensor with shape ``[batch_size_per_im * batch_size, 4 * class_num]``. The weights of regression loss. The data type is the same as ``rpn_rois``.
scores(Variable): A 4-D Tensor with shape [N, A, H, W] represents
the probability for each box to be an object.
N is batch size, A is number of anchors, H and W are height and
width of the feature map.
width of the feature map. The data type must be float32.
bbox_deltas(Variable): A 4-D Tensor with shape [N, 4*A, H, W]
represents the differece between predicted box locatoin and
anchor location.
anchor location. The data type must be float32.
im_info(Variable): A 2-D Tensor with shape [N, 3] represents origin
image information for N batch. Info contains height, width and scale
between origin image size and the size of feature map.
The data type must be int32.
anchors(Variable): A 4-D Tensor represents the anchors with a layout
of [H, W, A, 4]. H and W are height and width of the feature map,
num_anchors is the box count of each position. Each anchor is
in (xmin, ymin, xmax, ymax) format an unnormalized.
variances(Variable): The expanded variances of anchors with a layout of
in (xmin, ymin, xmax, ymax) format an unnormalized. The data type must be float32.
variances(Variable): A 4-D Tensor. The expanded variances of anchors with a layout of
[H, W, num_priors, 4]. Each variance is in
(xcenter, ycenter, w, h) format.
(xcenter, ycenter, w, h) format. The data type must be float32.
pre_nms_top_n(float): Number of total bboxes to be kept per
image before NMS. 6000 by default.
image before NMS. The data type must be float32. `6000` by default.
post_nms_top_n(float): Number of total bboxes to be kept per
image after NMS. 1000 by default.
nms_thresh(float): Threshold in NMS, 0.5 by default.
image after NMS. The data type must be float32. `1000` by default.
nms_thresh(float): Threshold in NMS. The data type must be float32. `0.5` by default.
min_size(float): Remove predicted boxes with either height or
width < min_size. 0.1 by default.
eta(float): Apply in adaptive NMS, if adaptive threshold > 0.5,
adaptive_threshold = adaptive_threshold * eta in each iteration.
width < min_size. The data type must be float32. `0.1` by default.
eta(float): Apply in adaptive NMS, if adaptive `threshold > 0.5`,
`adaptive_threshold = adaptive_threshold * eta` in each iteration.
Returns:
tuple:
A tuple with format ``(rpn_rois, rpn_roi_probs)``.
- **rpn_rois**: The generated RoIs. 2-D Tensor with shape ``[N, 4]`` while ``N`` is the number of RoIs. The data type is the same as ``scores``.
- **rpn_roi_probs**: The scores of generated RoIs. 2-D Tensor with shape ``[N, 1]`` while ``N`` is the number of RoIs. The data type is the same as ``scores``.
the input feature map should be sampled to produce the transformed
output feature map.
.. code-block:: text
* Case 1:
Given:
theta = [[[x_11, x_12, x_13]
[x_14, x_15, x_16]]
[[x_21, x_22, x_23]
[x_24, x_25, x_26]]]
out_shape = [2, 3, 5, 5]
Step 1:
Generate normalized coordinates according to out_shape.
The values of the normalized coordinates are in the interval between -1 and 1.
The shape of the normalized coordinates is [2, H, W] as below:
C = [[[-1. -1. -1. -1. -1. ]
[-0.5 -0.5 -0.5 -0.5 -0.5]
[ 0. 0. 0. 0. 0. ]
[ 0.5 0.5 0.5 0.5 0.5]
[ 1. 1. 1. 1. 1. ]]
[[-1. -0.5 0. 0.5 1. ]
[-1. -0.5 0. 0.5 1. ]
[-1. -0.5 0. 0.5 1. ]
[-1. -0.5 0. 0.5 1. ]
[-1. -0.5 0. 0.5 1. ]]]
C[0] is the coordinates in height axis and C[1] is the coordinates in width axis.
Step2:
Tanspose and reshape C to shape [H * W, 2] and append ones to last dimension. The we get:
C_ = [[-1. -1. 1. ]
[-0.5 -1. 1. ]
[ 0. -1. 1. ]
[ 0.5 -1. 1. ]
[ 1. -1. 1. ]
[-1. -0.5 1. ]
[-0.5 -0.5 1. ]
[ 0. -0.5 1. ]
[ 0.5 -0.5 1. ]
[ 1. -0.5 1. ]
[-1. 0. 1. ]
[-0.5 0. 1. ]
[ 0. 0. 1. ]
[ 0.5 0. 1. ]
[ 1. 0. 1. ]
[-1. 0.5 1. ]
[-0.5 0.5 1. ]
[ 0. 0.5 1. ]
[ 0.5 0.5 1. ]
[ 1. 0.5 1. ]
[-1. 1. 1. ]
[-0.5 1. 1. ]
[ 0. 1. 1. ]
[ 0.5 1. 1. ]
[ 1. 1. 1. ]]
Step3:
Compute output by equation $$Output[i] = C_ * Theta[i]^T$$
Args:
theta (Variable): A batch of affine transform parameters with shape [N, 2, 3].
out_shape (Variable | list | tuple): The shape of target output with format [N, C, H, W].
``out_shape`` can be a Variable or a list or tuple.
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
Args:
theta (Variable) - A Tensor with shape [N, 2, 3]. It contains a batch of affine transform parameters.
The data type can be float32 or float64.
out_shape (Variable | list | tuple): The shape of target output with format [batch_size, channel, height, width].
``out_shape`` can be a Tensor or a list or tuple. The data
type must be int32.
name(str|None): The default value is None. Normally there is no need for user to set this property. For more information, please refer to :ref:`api_guide_Name`.
Returns:
Variable: The output with shape [N, H, W, 2].
Variable: A Tensor with shape [batch_size, H, W, 2] while 'H' and 'W' are the height and width of feature map in affine transformation. The data type is the same as `theta`.
Raises:
ValueError: If the type of arguments is not supported.
