Anyone can provide a detailed tutorial of how to convert FasterRCNN caffe models to FasterRCNN SNPE models ? Specifically, how can I set the PRE_NMS_TOP_N and POST_NMS_TOP_N for the Proposal Layer ?
Also, R-FCN is a very popular improvement on FasterRCNN. It would be great if future SNPE revisions support R-FCN-based object detection algorithms.
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 have converted Faster-RCNN caffe models to dlc models. You should provide the params of proposal layer in Python type.