Add support for tflite arg_min and arg_max #5992
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* this implementation supports only the case when the axis is a scalar * tflite 1.13 removes all dims of size 1, Relay doesn't do this * WARNING: every newer version of tflite > 1.13 needs keepdims=TRUE
keepdims set to False and added some checks Note the unit tests emmitted following warning: /workspace/src/te/schedule/bound.cc:119: not in feed graph consumer = compute(T_multiply_red_temp, 0x53f5050)
d-smirnov
changed the title
MarisaKirisame
approved these changes
Jul 4, 2020
|
@d-smirnov can you get some other ppl to review as well? |
siju-samuel
requested changes
Jul 4, 2020
python/tvm/relay/frontend/tflite.py
Outdated
| def _convert_arg_min_max(self, relay_op, op): | ||
| """Generic method to convert TFLite arg_min_max""" | ||
| try: | ||
| from tflite.Operator import Operator |
There was a problem hiding this comment.
is something like this?
def convert_arg_max(self, op):
"""Convert TFLite ARG_MAX"""
if self.is_quantized(op):
raise tvm.error.OpNotImplemented(
'TFlite quantized ARG_MAX operator is not supported yet.')
return self._convert_unary_elemwise(_op.arg_max, op)
Removed quantized argmin due to inablility to provide proper test case
siju-samuel
reviewed
Jul 9, 2020
anijain2305
approved these changes
Jul 13, 2020
|
Thanks @d-smirnov @siju-samuel @MarisaKirisame This is merged! |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Jul 14, 2020
* [Relay][Frontend][TFLite] Add parser support for arg_min_max * this implementation supports only the case when the axis is a scalar * tflite 1.13 removes all dims of size 1, Relay doesn't do this * WARNING: every newer version of tflite > 1.13 needs keepdims=TRUE * Migrated to tflite 2.1.0 keepdims set to False and added some checks Note the unit tests emmitted following warning: /workspace/src/te/schedule/bound.cc:119: not in feed graph consumer = compute(T_multiply_red_temp, 0x53f5050) * linter * Removed quantized argmin Removed quantized argmin due to inablility to provide proper test case * added negative ranges * re-trigger CI Co-authored-by: Ina_Dobreva <Ina.Dobreva@arm.com>
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Jul 14, 2020
* [Relay][Frontend][TFLite] Add parser support for arg_min_max * this implementation supports only the case when the axis is a scalar * tflite 1.13 removes all dims of size 1, Relay doesn't do this * WARNING: every newer version of tflite > 1.13 needs keepdims=TRUE * Migrated to tflite 2.1.0 keepdims set to False and added some checks Note the unit tests emmitted following warning: /workspace/src/te/schedule/bound.cc:119: not in feed graph consumer = compute(T_multiply_red_temp, 0x53f5050) * linter * Removed quantized argmin Removed quantized argmin due to inablility to provide proper test case * added negative ranges * re-trigger CI Co-authored-by: Ina_Dobreva <Ina.Dobreva@arm.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
"Add support for tflite arg_min and arg_max"
This is an updated version of abandoned PR [Relay][Frontend][TFLite] Add parser support for arg_min_max #4704 rebased on top of current master with small updates related to tflite 2.1.0.
Please note unit tests for arg_max and arg_min emit following warning:
/workspace/src/te/schedule/bound.cc:119: not in feed graph consumer = compute(T_multiply_red_temp, 0x53f5050)