leandron commented on code in PR #10915: URL: https://github.com/apache/tvm/pull/10915#discussion_r875007604
########## src/relay/qnn/op/convolution.cc: ########## @@ -829,7 +839,7 @@ This operator convolves quantized weight with quantized data. The scale of the output quantized tensor is the product of the weight_scale and input_scale of the input quantized tensors. The zero point of the output quantized tensor is 0. By default, the dtype of output is int32. Please also refer to Requantize -operator to understand how to scale back the int32 output to (u)int8. +operator to understand how to scale back the int32 output to (u)int8 or (u)int16. Review Comment: Yes, it can be used as a quantized tensor type and for input/output for the model, generally in TFLite. However, the internal [converter quantization functionality](https://www.tensorflow.org/lite/performance/post_training_integer_quant_16x8) only converts to int16, not uint16. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
