FPS

[jordanlai]

Hi
I have a question.
In the test video:
python openvino_tiny-yolov3_test.py -d MYRIAD
--> get FPS=13
python openvino_tiny-yolov3_test.py -d CPU
--> get FPS=35
which side is out the question?
Thanks!

[PINTO0309]

python openvino_tiny-yolov3_test.py -d MYRIAD
--> get FPS=13

Correct result.

python openvino_tiny-yolov3_test.py -d CPU
--> get FPS=35

Correct result.

OpenVINO is fully optimized for Intel CPUs with Intel TBB and Intel MKL-DNN. You'll see that using the GPU with the -d GPU option results in a percentage of slower performance than CPU performance. The more logical cores you have on your CPU, the more performance will increase.

[jordanlai]

@PINTO0309
Thanks

[jordanlai]

Another question is as follows
autumn-openvino@autumn:~/inference_engine_samples_build/intel64/Release$ ./object_detection_demo_yolov3_async -i /home/autumn-openvino/OpenVINO-YoloV3-master_0309/data/input/2.mp4 -m /home/autumn-openvino/桌面/openvino_out/yolov3-tiny_416.xml -d MYRIAD
InferenceEngine:
API version ............ 1.6
Build .................. custom_releases/2019/R1_ebce9728578ef3131f2f282b3fbc3232109c598e
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading plugin

API version ............ 1.6
Build .................. 23224
Description ....... myriadPlugin

[ INFO ] Loading network files
[ INFO ] Batch size is forced to 1.
[ INFO ] Checking that the inputs are as the demo expects
[ INFO ] Checking that the outputs are as the demo expects
[ ERROR ] This demo only accepts networks with three layers

I train model yolov3-tiny
size=416

[PINTO0309]

https://github.com/PINTO0309/OpenVINO-YoloV3/tree/b5caa1c2117749b84719c0cd9750c10c452ef471/cpp#recompile
Please read my main.cpp. The Intel sample program and my program are different.

OpenVINO-YoloV3/cpp/main.cpp

Lines 308 to 310 in b5caa1c

	//if (outputInfo.size() != 3) {
	// throw std::logic_error("This demo only accepts networks with three layers");
	//}