-
Notifications
You must be signed in to change notification settings - Fork 82
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
[TensorV2] Add Transpose Support for Tensor #2475
[TensorV2] Add Transpose Support for Tensor #2475
Conversation
📝 TAOS-CI Version: 1.5.20200925. Thank you for submitting PR #2475. Please a submit 1commit/1PR (one commit per one PR) policy to get comments quickly from reviewers. Your PR must pass all verificiation processes of cibot before starting a review process from reviewers. If you are new member to join this project, please read manuals in documentation folder and wiki page. In order to monitor a progress status of your PR in more detail, visit http://ci.nnstreamer.ai/. |
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.
@djeong20, 💯 All CI checkers are successfully verified. Thanks.
|
||
switch (from.getDataType()) { | ||
case ml::train::TensorDim::DataType::FP32: | ||
scopy(size(), from.getData<float>(), 1, (_FP16 *)getData(), 1); |
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.
Using swich-case instead of previous if-else seems much better!
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!
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
@@ -21,6 +21,34 @@ | |||
#include <tensor_dim.h> | |||
#include <util_func.h> | |||
|
|||
#define transposeloop(cl, ci, cj, ck, sl, si, sj, sk) \ |
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.
I'm not sure if it is working with omp directives in define. If it can, then we could try to apply it.
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.
agree. I think we should test it after when openMP is enabled. I'll keep it in mind and come back to this later.
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 except minor comment.
This pull request adds the ability to transpose tensors, which allows users to flip or rotate their data along its axes. **Changes proposed in this PR:** - Added a new method called transpose() to the TensorV2 class, which takes direction argument: the axes to be swapped. **Self-evaluation:** 1. Build test: [X]Passed [ ]Failed [ ]Skipped 2. Run test: [X]Passed [ ]Failed [ ]Skipped Signed-off-by: Donghyeon Jeong <[email protected]>
f4d5741
to
6d4a6e5
Compare
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.
@djeong20, 💯 All CI checkers are successfully verified. Thanks.
Currently, the TAOS/CI clang-format version differs from Git action static checks. there's a mismatch that causes clang-format style error (the behavior of the clang-format varies for different versions). It is ok to merge. |
This pull request adds the ability to transpose tensors, which allows users to flip or rotate their data along its axes.
Changes proposed in this PR:
Self-evaluation: