Kind of Unet architecture works fine on CPU but generate corrupted result on GPU.
We have a kind of Unet which works fine on both devices (CPU and GPU), but when we reduce the number of generated convolutions in each layer by some constant factor, the GPU inference stop generate valid result (start to see garbage like vertical stripes instead of image). There is no errors or worming during model generation or inference, I am wandering if there is some memory alignment related to openCL and GPU that cause to this issue and does not taken into account by open vino?
just wanted to ask you, do you see the "same" Unet output in GPU FP32 and GPU FP16 modes?
My issue with Unet is that GPU in FP16 mode output is incorrect while GPU in FP32 mode is ok.
And MYRIAD FP16 output is ok.