1
0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 23:33:05 +04:00

Import SSDs from TensorFlow by training config (#12188)

* Remove TensorFlow and protobuf dependencies from object detection scripts

* Create text graphs for TensorFlow object detection networks from sample
This commit is contained in:
Dmitry Kurtaev
2018-09-03 17:08:40 +03:00
committed by Vadim Pisarevsky
parent e3af72bb68
commit c7cf8fb35c
10 changed files with 858 additions and 450 deletions
+8
View File
@@ -885,6 +885,14 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
CV_EXPORTS_W void shrinkCaffeModel(const String& src, const String& dst,
const std::vector<String>& layersTypes = std::vector<String>());
/** @brief Create a text representation for a binary network stored in protocol buffer format.
* @param[in] model A path to binary network.
* @param[in] output A path to output text file to be created.
*
* @note To reduce output file size, trained weights are not included.
*/
CV_EXPORTS_W void writeTextGraph(const String& model, const String& output);
/** @brief Performs non maximum suppression given boxes and corresponding scores.
* @param bboxes a set of bounding boxes to apply NMS.