I'm using snpe-dlc-quantize to quantize a tensorflow model MobileNetV1,then run it on DSP.But the result is wrong,unquantized model result is correct ,instead.
By the way,quantized caffe MobileNetV1 model which is running on DSP return correct results.
I've tried using use_enhanced_quantizer ,but make no difference.So Is there any way to solve the problem?
snpe version:1.22