Is there a problem about upsampling in snpe_caffe_to_dlc.py?
if use scale, upsample_h, upsample_w fields from upsample, should the input_dim[0] be the batch size? why use input_dim[0]*scale as the output_height?
i use upsample layer, the input data size is 1*16*16*128 and use upsample scale 2, the output data size is 1*32*32*16.
can anyone help me, please?
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.
