tflite computes the downscale and right shift integer parameters from a double input as they do in the call to Quantize Multiplier
` https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/experimental/micro/kernels/conv.cc ` > double real_multiplier = 0.0; > TF_LITE_ENSURE_STATUS(GetQuantizedConvolutionMultipler( > context, input, filter, bias, output, &real_multiplier)); > int exponent; > Quantize Multiplier(real_multiplier, &data->output_multiplier, &exponent); > data->output_shift = -exponent; > I'd suggest you print out their downscale and shift values for comparison, since errors can start there. Their downscale operations are implemented in int64. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2351#issuecomment-509085662
