Commit 70a3a612 by Ina Dobreva Committed by Tianqi Chen

Add support for quant. mul operator in tflite frontend (#4283)

A test for qnn_mul has to be added when the qnn elemwise tests (#4282) get merged.
parent 7dca6552
...@@ -575,8 +575,7 @@ class OperatorConverter(object): ...@@ -575,8 +575,7 @@ class OperatorConverter(object):
"""Convert TFLite MUL""" """Convert TFLite MUL"""
# Check if the input tensor is quantized, call QNN op # Check if the input tensor is quantized, call QNN op
if self.is_quantized(op): if self.is_quantized(op):
raise tvm.error.OpNotImplemented( return self._convert_elemwise(_qnn.op.mul, op)
'TFlite quantized mul operator is not supported yet.')
return self._convert_elemwise(_op.multiply, op) return self._convert_elemwise(_op.multiply, op)
def convert_div(self, op): def convert_div(self, op):
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment