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?