-
Notifications
You must be signed in to change notification settings - Fork 1.3k
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
[tmva][sofie] Add new operators and function to check input ONNX model #17248
Open
lmoneta
wants to merge
6
commits into
root-project:master
Choose a base branch
from
lmoneta:tmva_sofie_operator_devs
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
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
- optimize broadcast for the special case of last dim and add interface avoiding allocations - optimize Expand and Binary to use new broadcast interface
A new function has been added to check the model operators (nodes) and print the list of missing ones (not yet supported) To use it do: ``` TMVA::Experimental::SOFIE::RModelParser_ONNX p; bool ret = p.CheckModel("model.onnx"); ``` It will return true if all operators of the model are supported. In case of missing ones, it will print their list. The check will also extend to subgraph presented in the model as attributes of some specific nodes (e.g. of If operator)
Add new pad operator and a corresponding test. Fix also the parsing of Constant in case explicitly the data are not stored as raw_data in the onnx::TensorProto class
lmoneta
force-pushed
the
tmva_sofie_operator_devs
branch
from
December 11, 2024 13:15
9075077
to
8a7d0d4
Compare
Test Results 18 files 18 suites 3d 23h 3m 4s ⏱️ Results for commit 4b12e44. ♻️ This comment has been updated with latest results. |
Rename the RModel function IsINputTensor because was valid only for tensors without a defined shape. Add function IsReadyInputTensor to check if a tensor with a defined shape is an input tensor of the model This change avoids confusion
Add support for new operator Where and add corrisponding test Fix broadcasting of tensor in case of boolean tensor where one uses a std::vector<bool> instead of a span of bool
lmoneta
changed the title
[tmva][sofie] Add new Pad operator and a funciton to check ONNX model
[tmva][sofie] Add new operators and a funciton to check ONNX model
Dec 12, 2024
lmoneta
changed the title
[tmva][sofie] Add new operators and a funciton to check ONNX model
[tmva][sofie] Add new operators and function to check input ONNX model
Dec 12, 2024
2 tasks
Add Sin and Cos operators as new Unary operators. Add also tests, taken from Vedant's PR root-project#16809
lmoneta
force-pushed
the
tmva_sofie_operator_devs
branch
from
December 13, 2024 11:18
812964f
to
4b12e44
Compare
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.
This Pull request adds these new operators (including their tests):
In addition, implement:
Example of usage: