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?
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
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?