-
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
[Frontend][TENSORFLOW] Add support for unpack with dim 0 after tensorlist stack #8558
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
zxy844288792
requested review from
anijain2305,
areusch,
comaniac,
Huyuwei,
jroesch,
junrushao,
jwfromm,
kazum,
MarisaKirisame,
mbrookhart,
merrymercy,
siju-samuel,
slyubomirsky,
srkreddy1238,
tqchen,
vinx13,
wweic,
yzhliu,
zhiics and
ZihengJiang
as code owners
July 26, 2021 18:51
comaniac
requested changes
Jul 26, 2021
comaniac
approved these changes
Jul 26, 2021
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Jul 26, 2021
* enable testcase when tensorlist stack follows by a unpack for dim 0 * address reviews and improve the docstring
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Sep 29, 2021
…list stack (apache#8558) * enable testcase when tensorlist stack follows by a unpack for dim 0 * address reviews and improve the docstring
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Jan 13, 2022
…list stack (apache#8558) * enable testcase when tensorlist stack follows by a unpack for dim 0 * address reviews and improve the docstring
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.
In current unpack implementation:
tvm/python/tvm/relay/frontend/tensorflow_ops.py
Line 2557 in 9c63f4f
Any() is not supported and in some tf2 models from tf model hub like ssd_mobilenet_v2, we encounter some cases when unpack is after a tensorlist stack node. And the output for tensorlist stack will have any() in its dimension 0:
tvm/python/tvm/relay/prelude.py
Line 577 in 9c63f4f
In this case it will not supported.
This pr adds support by introducing an special case handling, when we know the tensorlist stack node input only contains one element, it will have output shape with 1 in dimension 0.