[TensorV2] Add utility member functions to TensorV2 class @open sesame 03/07 10:42 #2489
Conversation
djeong20
requested review from
myungjoo,
jijoongmoon,
again4you,
jaeyun-jung,
leemgs,
wooksong,
helloahn,
kparichay,
gichan-jang,
anyj0527,
zhoonit,
lhs8928,
songgot,
jihochu,
DonghakPark,
SeoHyungjun,
baek2sm,
skykongkong8,
EunjuYang and
a team
as code owners
|
📝 TAOS-CI Version: 1.5.20200925. Thank you for submitting PR #2489. 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/. |
DonghakPark
changed the title
djeong20
force-pushed
the
feat/tensor_v2/utils
branch
from
1a667ba
to
c657fe4
Compare
djeong20
force-pushed
the
feat/tensor_v2/utils
branch
from
c657fe4
to
c88b850
Compare
| * @param[in] d tensor dim | ||
| * @param[in] offset offset to be used from current | ||
| * @return Tensor object | ||
| * @throws std::invalid_argument if buf is null |
There was a problem hiding this comment.
Adding a note that the buffer is not owned by the mapped tensor would be better.
the user may be confused.
| std::default_delete<MemoryData>()); | ||
| offset = offset; | ||
| } | ||
|
|
There was a problem hiding this comment.
Could you explain a little bit more about this function's purpose? Just curious because I have not seen this in, let's say, TensorV1
There was a problem hiding this comment.
this is simply a helper function to set certain TensorBase variables in the Tensor class.
since Map() is a static function, the possible way to set TensorBase variables would be using a Tensor public function.
therefore, the SetTensorVar() function has been newly added.
This pull request adds several new utility member functions to the TensorV2 class, enabling users to perform various tasks with their tensors more easily and efficiently. These include saving and loading tensors, updating batches, getting argmax and max absolute values, and more. The implementation is based on the current Tensor class and aims to improve the overall usability and flexibility of the TensorV2 class. **Changes proposed in this PR:** - Added save() and read() methods to allow saving and loading of saved tensor data. - Added Map() method to create a new Tensor object from a buffer. - Added argmax() and max_abs() methods to retrieve the indices of max value by batch and the value of the maximum absolute element in a tensor. - Added updateBatch() to update tensor batch size. **Self-evaluation:** 1. Build test: [X]Passed [ ]Failed [ ]Skipped 2. Run test: [X]Passed [ ]Failed [ ]Skipped Signed-off-by: Donghyeon Jeong <[email protected]>
djeong20
force-pushed
the
feat/tensor_v2/utils
branch
from
c88b850
to
8611c3d
Compare
This pull request adds several new utility member functions to the TensorV2 class, enabling users to perform various tasks with their tensors more easily and efficiently.
These include saving and loading tensors, updating batches, getting argmax and max absolute values, and more.
The implementation is based on the current Tensor class and aims to improve the overall usability and flexibility of the TensorV2 class.
Changes proposed in this PR:
save()andread()methods to allow saving and loading of saved tensor data.Map()method to create a new Tensor object from a buffer.argmax()andmax_abs()methods to retrieve the indices of max value by batch and the value of the maximum absolute element in a tensor.updateBatch()to update tensor batch size.Self-evaluation: