Hi,
I have a working caffe model which I have converted with snpe-caffe-to-dlc with no errors, however I am not getting the expected output from the network when I test it either on android or using snpe-network-run.
After eliminating the input image format being wrong I finally isoloated the problem to the ReLU function not supporting the negative slope parameter - for a leaky relu (as defined below)
I think I have a work around using PReLU instead..
Hi Simon. Glad you found a workaround! And thanks for posting it for others to use.
SNPE doesn't support Leaky Relu at this time.
hi, jesliger, So is there a way to support the Leaky Relu?
Does the PReLU workaround that was posted not work for you? Leaky Relu is not in SNPE at this time. I'm hoping you can use PReLU for now.
I wonder how to fix the weight of PReLU in tensorflow, so it executes like leaky relu
Have you tested this on the DSP runtime? I observe huge accuracy errors on the DSP (compared to the other 2 runtimes) when using Prelu in lieu of leaky relu. Even when I reduce it to a basic ReLU by setting alpha to 0.