-
Notifications
You must be signed in to change notification settings - Fork 3.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Tracking issue] Quantized TFLite operators #9187
Comments
Hi @leandron can you please update this issue and if possible review the PR for qunatized SIN operator? Please let me know if I need to do any changes. |
Done! thanks @onkar-sima-ai |
Sorry I missed your message. I've just updated the list of operator. |
Support GREATER quantization operation conversion as part of issue apache#9187
Support EQUAL quantization operation conversion as part of issue apache#9187
* [TFLite] Support quantized EQUAL op in TFLite frontend Support EQUAL quantization operation conversion as part of issue #9187 * [TFLite] Support quantized EQUAL op in TFLite frontend Update elementwise quantized test for EQUAL op Change-Id: I3897d1ac07051ebfc10356ad45397117b592f878
* [TFLite] Support quantized EQUAL op in TFLite frontend Support EQUAL quantization operation conversion as part of issue apache#9187 * [TFLite] Support quantized EQUAL op in TFLite frontend Update elementwise quantized test for EQUAL op Change-Id: I3897d1ac07051ebfc10356ad45397117b592f878
Support GREATER quantization operation conversion as part of issue apache#9187 Continuation of apache#11519
Thanks @dchauhan-arm @leeexyz @onkar-sima-ai @elinx @ophirfrish for the contributions towards this effort! Closing as it is now complete. |
Support GREATER quantization operation conversion as part of issue apache#9187 Continuation of apache#11519.
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-armEQUAL
[TFLite] Support quantized EQUAL op in TFLite frontend #11520 @dchauhan-armCEIL
[TFLite] Quantized unary elemwise ops #10566 by @leeexyzROUND
[TFLite] Quantized unary elemwise ops #10566 by @leeexyzFLOOR
[TFLite] Quantized unary elemwise ops #10566 by @leeexyzEXP
[TFLite] Quantized unary elemwise ops #10566 by @leeexyzLOG
[TFLite] Quantized unary elemwise ops #10566 by @leeexyzSIN
added tests for quantized tflite sin operator #9478 by @onkar-sima-aiTAN
[TFLite] Quantized unary elemwise ops #10566 by @leeexyzCOS
[TFLite] Quantized unary elemwise ops #10566 by @leeexyzSQRT
Support quantised SQRT operator in TFLite #9258 by @elinxRSQRT
Support quantised RSQRT operator in TFLite #9165 by @ophirfrishNEG
Support quantized NEG operator in TFLite frontend #9404 by @ophirfrishFor each operator above, there are actions to be taken:
if self.is_quantized(op): ...
#9165 can be used as an example.
Resources:
The text was updated successfully, but these errors were encountered: