duangenquan

I added [a python wrapper based on boost](https://github.com/duangenquan/bhtsne), which process smoothly and visualize results at last. There is not need to recompile blas/numpy/etc. Hope this helps!

Could you share the config file you are using?

It looks like caffe python environment is not correct. Could you confirm this and then try again?

yes please.

do you have an easy way to switch to the new ncsdk2 API? Or will it detect the hardware automatically?

I do not have a VPU in hand right now. Please list any issues here if you could not run this repo in VPU. All source codes are mainly c/c++,...

Regionlayer is re-implemented in [this repo](https://github.com/duangenquan/YoloV2NCS) in c/c++, along with a python wrapper. Have fun!

I am afraid that some layers in yolov3 are not supported, such as "route","upsample" etc. You might need to update [create_yolo_caffemodel.py](https://github.com/duangenquan/YoloV2NCS/blob/master/python/create_yolo_caffemodel.py).

If NCSDK shows the sources codes of layers and they way to compile APIs, we can try to convert the customized layers in Yolo to NCSD. But I could not...

You can train yolo with your own categories, and follow "How to Use" and "Run Other YoloV2 models" sections to convert your own models.