-
Notifications
You must be signed in to change notification settings - Fork 3.8k
Closed
Description
As part of #9165, we recently enabled support for quantized operators in the TFLite frontend "unary element-wise" function, that does generic support for a few operators.
That opens the door for more operators to be supported easily, just pending the addition of tests and logically unlocking the conditional block that is keeping the quantised version of the operator to be unsupported. See the example as implemented in #9165.
This is a tracking issue for new unary element-wise operators to be supported:
-
GREATER[TFLite] Support quantized GREATER op in TFLite frontend #12754 @dchauhan-arm -
EQUAL[TFLite] Support quantized EQUAL op in TFLite frontend #11520 @dchauhan-arm -
CEIL[TFLite] Quantized unary elemwise ops #10566 by @leeexyz -
ROUND[TFLite] Quantized unary elemwise ops #10566 by @leeexyz -
FLOOR[TFLite] Quantized unary elemwise ops #10566 by @leeexyz -
EXP[TFLite] Quantized unary elemwise ops #10566 by @leeexyz -
LOG[TFLite] Quantized unary elemwise ops #10566 by @leeexyz -
SINadded tests for quantized tflite sin operator #9478 by @onkar-sima-ai -
TAN[TFLite] Quantized unary elemwise ops #10566 by @leeexyz -
COS[TFLite] Quantized unary elemwise ops #10566 by @leeexyz -
SQRTSupport quantised SQRT operator in TFLite #9258 by @elinx -
RSQRTSupport quantised RSQRT operator in TFLite #9165 by @ophirfrish -
NEGSupport quantized NEG operator in TFLite frontend #9404 by @ophirfrish
For each operator above, there are actions to be taken:
- Remove the conditional block
if self.is_quantized(op): ... - Implement unit tests
- ask any committer in the project to update this issue, reflecting the PR to support the operators on the list above
#9165 can be used as an example.
Resources: