p85971406
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!3040 BoundingBoxAugment op fix ratio 

Merge pull request !3040 from islam_amin/bounding_box_augment_bugs
This commit is contained in:
mindspore-ci-bot 2020-07-14 09:36:34 +08:00 committed by Gitee
parent 69ce4bf2b2 56da3b0ae1
commit 48654be14d
6 changed files with 32 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
mindspore/ccsrc/dataset/kernels/image/bounding_box_augment_op.cc
View File

@ -26,7 +26,7 @@ namespace dataset {
const float BoundingBoxAugmentOp::kDefRatio = 0.3;
BoundingBoxAugmentOp::BoundingBoxAugmentOp(std::shared_ptr<TensorOp> transform, float ratio)
: ratio_(ratio), transform_(std::move(transform)) {
: ratio_(ratio), uniform_(0, 1), transform_(std::move(transform)) {
rnd_.seed(GetSeed());
}
@ -34,41 +34,38 @@ Status BoundingBoxAugmentOp::Compute(const TensorRow &input, TensorRow *output)
IO_CHECK_VECTOR(input, output);
BOUNDING_BOX_CHECK(input); // check if bounding boxes are valid
uint32_t num_of_boxes = input[1]->shape()[0];
uint32_t num_to_aug = num_of_boxes * ratio_; // cast to int
std::vector<uint32_t> boxes(num_of_boxes);
std::vector<uint32_t> selected_boxes;
for (uint32_t i = 0; i < num_of_boxes; i++) boxes[i] = i;
// sample bboxes according to ratio picked by user
std::sample(boxes.begin(), boxes.end(), std::back_inserter(selected_boxes), num_to_aug, rnd_);
std::shared_ptr<Tensor> crop_out;
std::shared_ptr<Tensor> res_out;
std::shared_ptr<CVTensor> input_restore = CVTensor::AsCVTensor(input[0]);
for (uint32_t i = 0; i < num_to_aug; i++) {
float min_x = 0;
float min_y = 0;
float b_w = 0;
float b_h = 0;
// get the required items
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&min_x, {selected_boxes[i], 0}));
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&min_y, {selected_boxes[i], 1}));
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&b_w, {selected_boxes[i], 2}));
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&b_h, {selected_boxes[i], 3}));
RETURN_IF_NOT_OK(Crop(input_restore, &crop_out, static_cast<int>(min_x), static_cast<int>(min_y),
static_cast<int>(b_w), static_cast<int>(b_h)));
// transform the cropped bbox region
RETURN_IF_NOT_OK(transform_->Compute(crop_out, &res_out));
// place the transformed region back in the restored input
std::shared_ptr<CVTensor> res_img = CVTensor::AsCVTensor(res_out);
// check if transformed crop is out of bounds of the box
if (res_img->mat().cols > b_w || res_img->mat().rows > b_h || res_img->mat().cols < b_w ||
res_img->mat().rows < b_h) {
// if so, resize to fit in the box
std::shared_ptr<TensorOp> resize_op =
std::make_shared<ResizeOp>(static_cast<int32_t>(b_h), static_cast<int32_t>(b_w));
RETURN_IF_NOT_OK(resize_op->Compute(std::static_pointer_cast<Tensor>(res_img), &res_out));
res_img = CVTensor::AsCVTensor(res_out);
for (uint32_t i = 0; i < num_of_boxes; i++) {
// using a uniform distribution to ensure op happens with probability ratio_
if (uniform_(rnd_) < ratio_) {
float min_x = 0;
float min_y = 0;
float b_w = 0;
float b_h = 0;
// get the required items
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&min_x, {i, 0}));
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&min_y, {i, 1}));
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&b_w, {i, 2}));
RETURN_IF_NOT_OK(input[1]->GetItemAt<float>(&b_h, {i, 3}));
RETURN_IF_NOT_OK(Crop(input_restore, &crop_out, static_cast<int>(min_x), static_cast<int>(min_y),
static_cast<int>(b_w), static_cast<int>(b_h)));
// transform the cropped bbox region
RETURN_IF_NOT_OK(transform_->Compute(crop_out, &res_out));
// place the transformed region back in the restored input
std::shared_ptr<CVTensor> res_img = CVTensor::AsCVTensor(res_out);
// check if transformed crop is out of bounds of the box
if (res_img->mat().cols > b_w || res_img->mat().rows > b_h || res_img->mat().cols < b_w ||
res_img->mat().rows < b_h) {
// if so, resize to fit in the box
std::shared_ptr<TensorOp> resize_op =
std::make_shared<ResizeOp>(static_cast<int32_t>(b_h), static_cast<int32_t>(b_w));
RETURN_IF_NOT_OK(resize_op->Compute(std::static_pointer_cast<Tensor>(res_img), &res_out));
res_img = CVTensor::AsCVTensor(res_out);
}
res_img->mat().copyTo(input_restore->mat()(cv::Rect(min_x, min_y, res_img->mat().cols, res_img->mat().rows)));
}
res_img->mat().copyTo(input_restore->mat()(cv::Rect(min_x, min_y, res_img->mat().cols, res_img->mat().rows)));
}
(*output).push_back(std::move(std::static_pointer_cast<Tensor>(input_restore)));
(*output).push_back(input[1]);

1
mindspore/ccsrc/dataset/kernels/image/bounding_box_augment_op.h
View File

@ -53,6 +53,7 @@ class BoundingBoxAugmentOp : public TensorOp {
private:
float ratio_;
std::mt19937 rnd_;
std::uniform_real_distribution<float> uniform_;
std::shared_ptr<TensorOp> transform_;
};
} // namespace dataset

0
tests/st/networks/models/resnet50/src/resnet.py Normal file → Executable file
View File

BIN
tests/ut/data/dataset/golden/bounding_box_augment_crop_c_result.npz
View File

Binary file not shown.

BIN
tests/ut/data/dataset/golden/bounding_box_augment_valid_ratio_c_result.npz
View File

Binary file not shown.

4
tests/ut/python/dataset/test_bounding_box_augment.py
View File

@ -84,8 +84,8 @@ def test_bounding_box_augment_with_crop_op(plot_vis=False):
dataVoc1 = ds.VOCDataset(DATA_DIR, task="Detection", mode="train", decode=True, shuffle=False)
dataVoc2 = ds.VOCDataset(DATA_DIR, task="Detection", mode="train", decode=True, shuffle=False)
# Ratio is set to 1 to apply rotation on all bounding boxes.
test_op = c_vision.BoundingBoxAugment(c_vision.RandomCrop(50), 0.5)
# Ratio is set to 0.9 to apply RandomCrop of size (50, 50) on 90% of the bounding boxes.
test_op = c_vision.BoundingBoxAugment(c_vision.RandomCrop(50), 0.9)
# map to apply ops
dataVoc2 = dataVoc2.map(input_columns=["image", "annotation"],