Skip to content
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

Set default value of p in LpPool as 2 #8866

Merged
merged 5 commits into from
Sep 2, 2021
Merged

Set default value of p in LpPool as 2 #8866

merged 5 commits into from
Sep 2, 2021

Conversation

luyaor
Copy link
Contributor

@luyaor luyaor commented Aug 27, 2021

@jwfromm Sorry for very late update. Followed #7242.

I have already formatted the code based on #7242 (comment).

Hope to merge :)

@luyaor
Copy link
Contributor Author

luyaor commented Aug 31, 2021

@jwfromm @vinx13 Anyone know why tvm-ci/pr-merge is failed?

@vinx13
Copy link
Member

vinx13 commented Aug 31, 2021

Looks like the added test case in this PR doesn't pass CI, can you try this test case locally to see if it can be reproduced?

Fix bug in test.
@luyaor
Copy link
Contributor Author

luyaor commented Aug 31, 2021

Sorry, I incorrectly calculate the output shape of test input. It should be correct now. :)

@junrushao
Copy link
Member

Thanks Luyao! It all looks good to me

@vinx13
Copy link
Member

vinx13 commented Aug 31, 2021

@luyaor CI failed for unrelated things, could you push again to retrigger CI?

@junrushao
Copy link
Member

nvm I retriggered CI

@luyaor
Copy link
Contributor Author

luyaor commented Sep 1, 2021

Looks like frontend: GPU is failed but others are passed normally. Any one could check it out?

Copy link
Member

@vinx13 vinx13 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is the error on CI

E onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Node: Output:y [ShapeInferenceError] Can't merge shape info. Both source and target dimension have values but they differ. Source=32 Target=31 Dimension=2

Seems the previous output shape [1, 1, 32, 32] was correct?

Copy link
Contributor

@mbrookhart mbrookhart left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Other than the shape issue LGTM

tests/python/frontend/onnx/test_forward.py Outdated Show resolved Hide resolved
update with correct shape.
@luyaor
Copy link
Contributor Author

luyaor commented Sep 1, 2021

updated.

python/tvm/relay/frontend/onnx.py Outdated Show resolved Hide resolved
@luyaor luyaor requested a review from vinx13 September 2, 2021 02:11
@luyaor
Copy link
Contributor Author

luyaor commented Sep 2, 2021

Updated.

Co-authored-by: Wuwei Lin <vincentl13x@gmail.com>
@mbrookhart mbrookhart merged commit 7c9811c into apache:main Sep 2, 2021
@mbrookhart
Copy link
Contributor

Thanks @luyaor @vinx13 @junrushao1994 @jwfromm !

AndrewZhaoLuo added a commit to AndrewZhaoLuo/tvm that referenced this pull request Sep 2, 2021
* main:
  [UnitTests][Contrib] Enable contrib tensorrt/coreml unit tests (apache#8902)
  [BUG] DataType Bug In SplitRel (apache#8899)
  Enable python debug runtime for exported network libraries (apache#8793)
  Set default value of p in LpPool as 2 (apache#8866)
  [Community] @Hzfengsy -> Committer (apache#8908)
  Trivial uTVM -> microTVM "spelling" fix to align with branding. (apache#8905)
  [Vulkan][Topi] Parametrizing additional topi tests, marking vulkan failures (apache#8904)
  Move to new style issue template system (apache#8898)
  [Onnx] Support Negative Log Loss (apache#8872)
  [ROCm][TVMC] Add ROCm to the TVMC driver (apache#8896)
  fix error report on Store (apache#8895)
  [Docker] Re-enabled automatic --tty flag when running bash. (apache#8861)
ylc pushed a commit to ylc/tvm that referenced this pull request Sep 29, 2021
* Set default value of p in LpPool as 2

* Update test_forward.py

Fix bug in test.

* Update test_forward.py

update with correct shape.

* Update onnx.py

* Update python/tvm/relay/frontend/onnx.py

Co-authored-by: Wuwei Lin <vincentl13x@gmail.com>

Co-authored-by: luyaor <luyaor@luyaordeMacBook-Pro.local>
Co-authored-by: Wuwei Lin <vincentl13x@gmail.com>
ylc pushed a commit to ylc/tvm that referenced this pull request Jan 13, 2022
* Set default value of p in LpPool as 2

* Update test_forward.py

Fix bug in test.

* Update test_forward.py

update with correct shape.

* Update onnx.py

* Update python/tvm/relay/frontend/onnx.py

Co-authored-by: Wuwei Lin <vincentl13x@gmail.com>

Co-authored-by: luyaor <luyaor@luyaordeMacBook-Pro.local>
Co-authored-by: Wuwei Lin <vincentl13x@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants