I am trying to run YOLO on SNPE but the classification of an image it's always wrong. I convert the .cfg and .weight file in .prototxt and .caffemodel, and then the .prototxt and .caffemodel in .dlc file using snpe-caffe-to-dlc tool, but the classification always fail. Can somebody tell me the correct steps to run yolo on SNPE?
YOLO and SNPE
Posted: Wed, 2018-11-14 04:10
I am trying
Can you write here if you do it? Thanks! It's for my final university exam and I am a little bit worry.
Hi,
For your kind information, the SNPE do not have any support for pre-processing the image.
Can you please confirm, if the image provided is preprocessed according to input required by YOLO model's architecture to classify them. Ex: image dimensions, normalization on the image... etc
hey! Luca, I met the same problem, have you solved it?
Is it caused by image pre-processing?