Comments (4)
Thanks @tqchen and congrats on releasing nnvm/tvm!
Here are my 2 cents:
- ONNX has a value as a spec that is serializable and framework-independent. Thus it's explicitly put separately from any framework or toolchain, but it's welcoming contribution both to the spec and to importers/exporters
- we totally share the view that the more standardized the community stack becomes - the better. For example, even if in-memory IR representations are different code, it's easier if they share the same operator semantics
- we'd be very happy to collaborate on making NNVM/TVM stack work smoothly with ONNX and we're welcoming spec suggestions as well
- you've mentioned great topics for discussion - we're always happy to have a exchange experience on tech issues and lessons learned
from onnx.
@tqchen There are certainly ambitions to have a good shared in-memory graph structure to facilitate further collaboration on graph-based optimizations.
from onnx.
@yuanbyu For in-memory graph structure, I would recommend nnvm as one of a starting point, as it already being framework agnostic and comes with a bunch of graph optimizations that already provides end to end compilation for onnx. And we would be more than happy to get involved in the discussion
from onnx.
i am going to close this for now as specific discussion can happen in separate issues
from onnx.
Related Issues (20)
- Create test for validating shape-inference methods handle unknown rank inputs
- Define DepthToSpace as function
- Using Pytorch Count of input_names provided during export not matching with session.get_inputs() HOT 1
- ONNX is broken when built with ONNX_USE_LITE_PROTO=OFF (using protobuf-24.4): File already exists in database: onnx/onnx-ml.proto HOT 5
- Schema error trying to create new version of training ops
- ERROR: Could not build wheels for onnx which use PEP 517 and cannot be installed directly HOT 2
- output different between onnx and pytorch HOT 7
- Implement DepthToSpace as a function HOT 2
- Reference implementation of ONNX Reduce sum square is mismatch with ONNX Spec when noop_with_empty_axes == 1 HOT 5
- Clarification of Reshape semantics for attribute 'allowzero' NOT set, zero volume HOT 3
- Change dynamic shape in fixed shape using C++ HOT 1
- The weekly model zoo CI has been failing HOT 12
- Incorrect input names for quantize/dequantize ONNX backend node tests HOT 1
- Fix and test numpy_helper to_array
- How to read onnx and obtain names, imgsz HOT 3
- Model zoo test failures HOT 1
- DequantizeLinear spec clarification: What happens if the subtraction overflows/underflows? HOT 1
- the model for UniqueOp in backend test is not always correct for different input
- A conflict doc abount compatibility between Onnx Version & ML Opset Version HOT 2
- [Shape Inference] Robustness of `ConstantOfShape` operator HOT 2
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 onnx.