This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

DRA756: Can I do Semantic Segmentation on this platform?

Part Number: DRA756

Hi there,

I went across the TI demo for semantic segmentation on CES 2017 earlier this year. Although the demo was carried out on TDA2x the video was very impressive. I'd like to know whether it is possible to get it done on J6 as the specs of the two platforms are quite similar.

If that's possible, can anyone point out the right instructions that I should follow. I have seen some previous posts on TIDL where caffe-jacinto was introduced (about sparse and quantified models). I am more interested in examples showing the inference of a neural net. Maybe I missed some info in that post. It would be very nice if someone could give me some suggestions regarding this topic.

Many thanks in advance.

Kind regards,

Matt