summaryrefslogtreecommitdiff
path: root/mv_machine_learning/object_detection/include/MobilenetV2Ssd.h
blob: 0df2bebe2bdfaa7bb9c0ace4591e7c3ba06d49bb (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
/**
 * Copyright (c) 2023 Samsung Electronics Co., Ltd All Rights Reserved
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#ifndef __MOBILENET_V2_SSD_H__
#define __MOBILENET_V2_SSD_H__

#include "mv_private.h"
#include <memory>
#include <mv_common.h>
#include <string>

#include "ObjectDetection.h"
#include <mv_inference_type.h>

namespace mediavision
{
namespace machine_learning
{
template<typename T> class MobilenetV2Ssd : public ObjectDetection<T>
{
	using ObjectDetection<T>::_config;
	using ObjectDetection<T>::_preprocess;
	using ObjectDetection<T>::_labels;

private:
	ObjectDetectionResult _result;

	void ApplyNms(std::vector<std::vector<Box> > &box_lists, BoxNmsMode mode, float threshold,
				  std::vector<Box> &box_vector);
	Box decodeBox(const DecodingBox *decodingBox, std::vector<float> &bb_tensor, int idx, float score, int label,
				  int box_offset);
	Box decodeBoxWithAnchor(const BoxAnchorParam *boxAnchorParam, Box &box, cv::Rect2f &anchor);

public:
	MobilenetV2Ssd(ObjectDetectionTaskType task_type, std::shared_ptr<Config> config);
	~MobilenetV2Ssd();

	ObjectDetectionResult &result() override;
};

} // machine_learning
} // mediavision

#endif