mindspore-Ecosystem
/
mindspore
21
0
Fork 27
Code Issues Pull Requests 6 Projects Releases Wiki Activity

!4558 soft_dvpp_decode_resize_jpeg_op issue resolved, input size can be an int, break the constraints of input size being sequence (height, width) 

Merge pull request !4558 from magemomou/my/work
This commit is contained in:
mindspore-ci-bot 2020-08-17 16:40:43 +08:00 committed by Gitee
parent 490a515b1f c410c6a6e2
commit f41ca6b5c6
5 changed files with 70 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
mindspore/ccsrc/minddata/dataset/kernels/image/soft_dvpp/soft_dvpp_decode_random_crop_resize_jpeg_op.cc
View File

@ -43,8 +43,8 @@ Status SoftDvppDecodeRandomCropResizeJpegOp::GetCropInfo(const std::shared_ptr<T
RETURN_IF_NOT_OK(GetCropBox(img_height, img_width, &x, &y, &crop_heigh, &crop_widht));
crop_info->left = x;
crop_info->up = y;
crop_info->right = crop_info->left + crop_widht;
crop_info->down = crop_info->up + crop_heigh;
crop_info->right = crop_info->left + crop_widht - 1;
crop_info->down = crop_info->up + crop_heigh - 1;
return Status::OK();
}

38
mindspore/ccsrc/minddata/dataset/kernels/image/soft_dvpp/soft_dvpp_decode_resize_jpeg_op.cc
View File

@ -15,6 +15,7 @@
*/
#include "minddata/dataset/kernels/image/soft_dvpp/soft_dvpp_decode_resize_jpeg_op.h"
#include <string>
#include <vector>
#include "./utils/external_soft_dp.h"
#include "opencv2/opencv.hpp"
@ -35,14 +36,32 @@ Status SoftDvppDecodeResizeJpegOp::Compute(const std::shared_ptr<Tensor> &input,
SoftDpProcsessInfo info;
info.input_buffer = static_cast<uint8_t *>(buffer);
info.input_buffer_size = input->SizeInBytes();
info.output_width = target_width_;
info.output_height = target_height_;
int input_w = 0;
int input_h = 0;
RETURN_IF_NOT_OK(GetJpegImageInfo(input, &input_w, &input_h));
SoftDpCropInfo crop_info{0, 0, 0, 0};
cv::Mat out_rgb_img(target_height_, target_width_, CV_8UC3);
if (target_width_ == 0) {
if (input_h < input_w) {
CHECK_FAIL_RETURN_UNEXPECTED(input_h != 0, "The input height is 0");
info.output_height = target_height_;
info.output_width = static_cast<int>(std::lround(static_cast<float>(input_w) / input_h * info.output_height));
} else {
CHECK_FAIL_RETURN_UNEXPECTED(input_w != 0, "The input width is 0");
info.output_width = target_height_;
info.output_height = static_cast<int>(std::lround(static_cast<float>(input_h) / input_w * info.output_width));
}
} else {
info.output_height = target_height_;
info.output_width = target_width_;
}
cv::Mat out_rgb_img(info.output_height, info.output_width, CV_8UC3);
info.output_buffer = out_rgb_img.data;
info.output_buffer_size = target_width_ * target_height_ * 3;
info.output_buffer_size = info.output_height * info.output_width * 3;
info.is_v_before_u = true;
int ret = DecodeAndResizeJpeg(&info);
std::string error_info("Soft dvpp DecodeAndResizeJpeg failed with return code: ");
@ -56,5 +75,16 @@ Status SoftDvppDecodeResizeJpegOp::Compute(const std::shared_ptr<Tensor> &input,
}
return Status::OK();
}
Status SoftDvppDecodeResizeJpegOp::OutputShape(const std::vector<TensorShape> &inputs,
std::vector<TensorShape> &outputs) {
RETURN_IF_NOT_OK(TensorOp::OutputShape(inputs, outputs));
outputs.clear();
TensorShape out({-1, -1, 3}); // we don't know what is output image size, but we know it should be 3 channels
if (inputs[0].Rank() == 1) outputs.emplace_back(out);
if (!outputs.empty()) return Status::OK();
return Status(StatusCode::kUnexpectedError, "Input has a wrong shape");
}
} // namespace dataset
} // namespace mindspore

2
mindspore/ccsrc/minddata/dataset/kernels/image/soft_dvpp/soft_dvpp_decode_resize_jpeg_op.h
View File

@ -18,6 +18,7 @@
#include <memory>
#include <string>
#include <vector>
#include "minddata/dataset/core/tensor.h"
#include "minddata/dataset/kernels/tensor_op.h"
@ -34,6 +35,7 @@ class SoftDvppDecodeResizeJpegOp : public TensorOp {
~SoftDvppDecodeResizeJpegOp() = default;
Status Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) override;
Status OutputShape(const std::vector<TensorShape> &inputs, std::vector<TensorShape> &outputs) override;
std::string Name() const override { return kSoftDvppDecodeReiszeJpegOp; }

2
mindspore/dataset/transforms/vision/c_transforms.py
View File

@ -943,7 +943,7 @@ class SoftDvppDecodeResizeJpeg(cde.SoftDvppDecodeResizeJpegOp):
@check_resize
def __init__(self, size):
if isinstance(size, int):
size = (size, size)
size = (size, 0)
self.size = size
super().__init__(*size)

31
tests/ut/python/dataset/test_soft_dvpp.py
View File

@ -84,7 +84,38 @@ def test_soft_dvpp_decode_random_crop_resize_jpeg(plot=False):
visualize_image(image1, image2, mse)
num_iter += 1
def test_soft_dvpp_decode_resize_jpeg_supplement(plot=False):
"""
Test SoftDvppDecodeResizeJpeg op
"""
logger.info("test_random_decode_resize_op")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = vision.Decode()
resize_op = vision.Resize(256)
data1 = data1.map(input_columns=["image"], operations=[decode_op, resize_op])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
soft_dvpp_decode_resize_op = vision.SoftDvppDecodeResizeJpeg(256)
data2 = data2.map(input_columns=["image"], operations=soft_dvpp_decode_resize_op)
num_iter = 0
for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()):
if num_iter > 0:
break
image1 = item1["image"]
image2 = item2["image"]
mse = diff_mse(image1, image2)
assert mse <= 0.02
logger.info("random_crop_decode_resize_op_{}, mse: {}".format(num_iter + 1, mse))
if plot:
visualize_image(image1, image2, mse)
num_iter += 1
if __name__ == "__main__":
test_soft_dvpp_decode_resize_jpeg(plot=True)
test_soft_dvpp_decode_random_crop_resize_jpeg(plot=True)
test_soft_dvpp_decode_resize_jpeg_supplement(plot=True)