Comments (12)
I have merged #42 and released v0.2.6. could you please try again with this latest version?
from optimizer.
Thanks for your issue!
What are "split_predict" and "lift_lexical_references" used for? I thought they are legacy passes and only useful for the caffe2 backend. Please correct me if I am wrong.
from optimizer.
Thanks for your issue!
What are "split_predict" and "lift_lexical_references" used for? I thought they are legacy passes and only useful for the caffe2 backend. Please correct me if I am wrong.
Hi @daquexian , yes this is a case from Caffe2 backend test. The background is that we are updating ONNX version under PyTorch, and was trying the onnxoptimizer module due to the dependency of Caffe2 on onnx.optimize. This error came up for these tests
TestCaffe2Backend_opset9::test_dynamic_loop
TestCaffe2Backend_opset9::test_loop
TestCaffe2Backend_opset9::test_nested_loops
from optimizer.
Is caffe2 backend still used? If needed I will take a look at it. Another choice is dropping the support for "lift_lexical_references" and "split_predict" passes if the only user -- caffe2 backend is deprecated.
from optimizer.
Hi @daquexian
Caffe2 backend is not updated recently, but the existing code and tests for older opsets are maintained as part of the repo.
This issue looks like a bug in the split_init_and_predict logic where nodes that are not in the predic net get deleted.
This is the CI for updating ONNX (currently failing): pytorch/pytorch#55889
Could you please take a look?
Thanks
from optimizer.
cc @gramalingam and @askhade
FYI, this issue is currently blocking the use of onnx/optimizer for us in: pytorch/pytorch#55889
from optimizer.
@BowenBao @neginraoof I'll take a look today tomorrow 😂
from optimizer.
@daquexian
Thanks for your help. This is currently needed for ONNX in PyTorch. Do you think we can help with anything here?
I can prepare a PR for split pass.
from optimizer.
I can prepare a PR for split pass.
Could you please submit a pr if applicable? I'm quite busy these days. 🤣 I'll take a look at this problem but it will help a lot if you also submit a pr
from optimizer.
@daquexian This is high priority for us as mentioned. Could you please take a look at the PR: #41
Thanks.
from optimizer.
I created a duplicate to check CI failures: #42
from optimizer.
@daquexian Also, would you please help us with the CI workflow issue?
from optimizer.
Related Issues (20)
- -1 mean dynamic shape or Static shape? HOT 2
- why using the same cmake but got error HOT 1
- Optimizer reports "Unresolved value references" since v0.3.0 HOT 1
- optimizer support for python 3.11 HOT 5
- CleanUnusedInitializersAndNodeArgs warning still issued after onnxoptimizer run HOT 1
- Support for python3.6 HOT 1
- If model use initializer, fuse_bn_into_conv is broken from v0.3.9 HOT 5
- error on model with sequence types/layers
- local functions missed when optimizing a model
- Question about building with released version ONNX
- optimization passes HOT 3
- Adding onnxoptimizer to conda-forge
- Fold LpNormalization
- Optimizer return an empty model HOT 1
- How to prohibit constant reuse HOT 2
- 3 concatenations at the same time?
- Failure to install on Python 3.12 HOT 3
- How to add customer fusion pass?
- [Feature request] Integrate Python-only API to ONNX optimizer proposal HOT 2
- Cannot Access Onnx Optimizer Web
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from optimizer.