Hello, I tranform my SSD Tensorflow model info dlc file. I would like to use snpe_sample compiled file to generate my boxes position. How could I do this?
Use SSD un cpp
Posted: Fri, 2018-03-09 10:00
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.
Just to add for more information. So I generate the mobilenet_ssd.dlc file and the raw files which size are 300x300.
During the generation of modelenet_ssd.dlc file I get that error but the file is well generated:
Then I generate the ouput for snpe-net-run:
./snpe-net-run --container ./mobilenet_ssd.dlc --input_list ../../models/inception_v3/data/cropped/raw_list.txt
For each images, it generates detection_classes:0.raw file.
The file is not empty but it seems to be the same for all images.
This is an example file I get :
http://www.filedropper.com/detectionclasses0