recently, I successfully convert the yolov3 to IR , but the new IR model size is too big. my openvino version is computer_vision_sdk_2018.4.420. I follow the doc directory :docs/_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_YOLO_From_Tensorflow.html to convert.
But the step I follow seems to some error, I failed. Then I modify the step as follow:
then the convertion success.
but I can not understand why that the models demo offered is so small and excellent performance,however the model I convert (yolov3) performance is pool and the size is large .
Can anyone help me ?
Hello Wang Nd,
> performance is pool and the size is large .
YOLO v3 is deep so performance may be poor but will be more accurate.
If you need better inference speed you may want to try tiny YOLO.
Thanks for your reply. I am also very interested in the small IR model the demos offered. eg: vehicle-attributes-recognition, I also test it. The performance is very Gei Li (Chinese words mean very excellent). I wander if I can also train the IR model directally (no convertion). Because the document has no mention about the IR model coming from. Currentlly I convert tensorflow and yolov3, I wish to know how to train such a small size model, so I can apply it to my application.