m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #13971 from sefira/FasterOpDoc

Browse Source 
generate proposal labels doc
fix_recordio_link
qingqing01 7 years ago committed by GitHub
parent 3c957af139 6c1d74bb47
commit cb27a9219d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 111 additions and 25 deletions
Show Stats Download Patch File Download Diff File

103
paddle/fluid/operators/detection/generate_proposal_labels_op.cc
Unescape View File

@ -439,31 +439,88 @@ class GenerateProposalLabelsKernel : public framework::OpKernel<T> {
class GenerateProposalLabelsOpMaker : public framework::OpProtoAndCheckerMaker {
public:
void Make() override {
// TODO(buxingyuan): Add Document
AddInput("RpnRois", "RpnRois.");
AddInput("GtClasses", "GtClasses.");
AddInput("IsCrowd", "IsCrowd.");
AddInput("GtBoxes", "GtBoxes.");
AddInput("ImInfo", "ImInfo.");
AddOutput("Rois", "Rois.");
AddOutput("LabelsInt32", "LabelsInt32.");
AddOutput("BboxTargets", "BboxTargets.");
AddOutput("BboxInsideWeights", "BboxInsideWeights.");
AddOutput("BboxOutsideWeights", "BboxOutsideWeights.");
AddAttr<int>("batch_size_per_im", "batch_size_per_im");
AddAttr<float>("fg_fraction", "fg_fraction");
AddAttr<float>("fg_thresh", "fg_thresh");
AddAttr<float>("bg_thresh_hi", "bg_thresh_hi");
AddAttr<float>("bg_thresh_lo", "bg_thresh_lo");
AddAttr<std::vector<float>>("bbox_reg_weights", "bbox_reg_weights");
AddAttr<int>("class_nums", "class_nums");
AddAttr<bool>("use_random", "use_random").SetDefault(true);
AddInput(
"RpnRois",
"(LoDTensor), This input is a 2D 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.");
AddInput("GtClasses",
"(LoDTensor), This input is a 2D LoDTensor with shape [M, 1]. "
"M is the number of groundtruth, "
"each element is a class label of groundtruth.");
AddInput(
"IsCrowd",
"(LoDTensor), This input is a 2D LoDTensor with shape [M, 1]. "
"M is the number of groundtruth, "
"each element is a flag indicates whether a groundtruth is crowd.");
AddInput(
"GtBoxes",
"(LoDTensor), This input is a 2D LoDTensor with shape [M, 4]. "
"M is the number of groundtruth, "
"each element is a bounding box with [xmin, ymin, xmax, ymax] format.");
AddInput("ImInfo",
"(Tensor), This input is a 2D Tensor with shape [B, 3]. "
"B is the number of input images, "
"each element consists of im_height, im_width, im_scale.");
AddOutput(
"Rois",
"(LoDTensor), This output is a 2D LoDTensor with shape [P, 4]. "
"P usuall equal to batch_size_per_im * batch_size, "
"each element is a bounding box with [xmin, ymin, xmax, ymax] format.");
AddOutput("LabelsInt32",
"(LoDTensor), This output is a 2D LoDTensor with shape [P], "
"each element repersents a class label of a roi");
AddOutput("BboxTargets",
"(LoDTensor), This output is a 2D LoDTensor with shape [P, 4 * "
"class_nums], "
"each element repersents a box label of a roi");
AddOutput(
"BboxInsideWeights",
"(LoDTensor), This output is a 2D LoDTensor with shape [P, 4 * "
"class_nums], "
"each element indicates whether a box should contribute to loss.");
AddOutput(
"BboxOutsideWeights",
"(LoDTensor), This output is a 2D LoDTensor with shape [P, 4 * "
"class_nums], "
"each element indicates whether a box should contribute to loss.");
AddAttr<int>("batch_size_per_im", "Batch size of rois per images.");
AddAttr<float>("fg_fraction",
"Foreground fraction in total batch_size_per_im.");
AddAttr<float>(
"fg_thresh",
"Overlap threshold which is used to chose foreground sample.");
AddAttr<float>("bg_thresh_hi",
"Overlap threshold upper bound which is used to chose "
"background sample.");
AddAttr<float>("bg_thresh_lo",
"Overlap threshold lower bound which is used to chose "
"background sample.");
AddAttr<std::vector<float>>("bbox_reg_weights", "Box regression weights.");
AddAttr<int>("class_nums", "Class number.");
AddAttr<bool>(
"use_random",
"Use random sampling to choose foreground and background boxes.")
.SetDefault(true);
AddComment(R"DOC(
Generate Proposals Labels Operator.
)DOC");
This operator can be, for given the GenerateProposalOp output bounding boxes and groundtruth,
to sample foreground boxes and background boxes, and compute loss target.
RpnRois is the output boxes of RPN and was processed by generate_proposal_op, these boxes
were combined with groundtruth boxes and sampled according to batch_size_per_im and fg_fraction,
If an instance with a groundtruth overlap greater than fg_thresh, then it was considered as a foreground sample.
If an instance with a groundtruth overlap greater than bg_thresh_lo and lower than bg_thresh_hi,
then it was considered as a background sample.
After all foreground and background boxes are chosen (so called Rois),
then we apply random sampling to make sure
the number of foreground boxes is no more than batch_size_per_im * fg_fraction.
For each box in Rois, we assign the classification (class label) and regression targets (box label) to it.
Finally BboxInsideWeights and BboxOutsideWeights are used to specify whether it would contribute to training loss.
)DOC");
}
};

33
python/paddle/fluid/layers/detection.py
Unescape View File

@ -1424,7 +1424,36 @@ def generate_proposal_labels(rpn_rois,
use_random=True):
"""
** Generate proposal labels Faster-RCNN **
TODO(buxingyuan): Add Document
This operator can be, for given the GenerateProposalOp output bounding boxes and groundtruth,
to sample foreground boxes and background boxes, and compute loss target.
RpnRois is the output boxes of RPN and was processed by generate_proposal_op, these boxes
were combined with groundtruth boxes and sampled according to batch_size_per_im and fg_fraction,
If an instance with a groundtruth overlap greater than fg_thresh, then it was considered as a foreground sample.
If an instance with a groundtruth overlap greater than bg_thresh_lo and lower than bg_thresh_hi,
then it was considered as a background sample.
After all foreground and background boxes are chosen (so called Rois),
then we apply random sampling to make sure
the number of foreground boxes is no more than batch_size_per_im * fg_fraction.
For each box in Rois, we assign the classification (class label) and regression targets (box label) to it.
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.
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.
bbox_reg_weights(list|tuple): Box regression weights.
class_nums(int): Class number.
use_random(bool): Use random sampling to choose foreground and background boxes.
"""
helper = LayerHelper('generate_proposal_labels', **locals())
@ -1487,7 +1516,7 @@ def generate_proposals(scores,
eta=1.0,
name=None):
"""
** Generate proposal labels Faster-RCNN **
** Generate proposal Faster-RCNN **
This operation proposes RoIs according to each box with their probability to be a foreground object and
the box can be calculated by anchors. Bbox_deltais and scores to be an object are the output of RPN. Final proposals

Write Preview
Loading…
Cancel
Save