Joshua

Results 10 issues of Joshua

I find run.py is updated. -# FLAGS.model = "darkflow/cfg/yolo.cfg" # tensorflow model -# FLAGS.load = "darkflow/bin/yolo.weights" # tensorflow weights -FLAGS.pbLoad = "tiny-yolo-voc-traffic.pb" # tensorflow model -FLAGS.metaLoad = "tiny-yolo-voc-traffic.meta" # tensorflow...

./build/FaceSDKDemo resources/image/1.jpg terminate called after throwing an instance of 'std::bad_alloc' what(): std::bad_alloc Aborted (core dumped)

一直是0%

I print the output of top 5, the score is such as:-0.18758957, 0.67330343, 2.45672223 ......... but I want to get the score such as: dog : 0.91 cat : 0.23...

开始还以为支持,后面发现manifest都没有

如图,我看到readme里有对应的人脸和活体检测的demo 但sdk编译的UI只有描点,需要自己实现活体识别的:张嘴、眨眼这些逻辑和处理UI 我不想重复造轮子,所以问下能否都提供出来?或者通过什么渠道可以获取,请告知一下

在公司安全可信选型版本发现,我司的ncnn库里只有这个版本是可信的 https://github.com/Tencent/ncnn/releases/download/20200727/ncnn-android-lib.zip 我们用的是yolo做检测,看了ncnn 20200727的修改记录,对应的应该是yolov4 如果要切换改版本,需要做哪些改动? 盼复!

[{"keyword":"离线","fscore":22.6},{"keyword":"场景","fscore":22.6}] 对于这样的json,keyword永远是"离线"