Open
Description
- Data model https://github.com/microsoft/onnx-rewriter/pull/232 https://github.com/microsoft/onnx-rewriter/pull/257
- Support tensor protos cleanly https://github.com/microsoft/onnx-rewriter/pull/254 https://github.com/microsoft/onnx-rewriter/pull/264
- [IR] Support dtypes that are not in numpy #1424
- [IR] User defined data types #1423
- Typing system: Unify Sequence types and Optional types https://github.com/microsoft/onnx-rewriter/pull/254 https://github.com/microsoft/onnx-rewriter/pull/264
- Tensor: implement nbytes, size and itemsize https://github.com/microsoft/onnx-rewriter/pull/254
- Use slots https://github.com/microsoft/onnx-rewriter/pull/254
-
Shared AttrRef in functions -
MakeOr we can "expand" itFunctioncallable.__call__(self, *values, *attrs) -> Sequence[Value](but still need to get the nodes); we can also just call a function to inline it? - Make
Functiona subclass ofGraph? #1360 - [IR] Safetensors support #1425
- [IR] Support empty outputs #1416
- [IR] Support Map type #1430
- [IR] Support symbolic values? #1438
- [IR] Point graph input and initializers back to the Graph #1440
- [IR] Data structure invariance #1450
- [IR] Tensor todos #1499
- [IR] Figure out how we can share tensors #1554
- [IR] Create a DEBUG flag to enable addtional checks #1545
- Use weakref for some bidirectional pointers / dictionaries
- For example, pointer in DiagnosticMessage?
- Serialization to proto https://github.com/microsoft/onnx-rewriter/pull/267
- Be careful to avoid copying
- Deserialization from proto https://github.com/microsoft/onnx-rewriter/pull/254
- Test serde with the ONNX test suite https://github.com/microsoft/onnx-rewriter/pull/267
-
User defined external data format in deserializer?They should handle them in a pass - [IR] Handle unsorted nodes #1426
- Mutation methods for graph; sorting
- https://github.com/microsoft/onnx-rewriter/pull/273
- [IR] Mutable IR implementation #1344
- Mutable protocols
- FX graph
- Immutable collection: https://github.com/pytorch/pytorch/blob/main/torch/fx/immutable_collections.py#L33
- [IR] Implement topological sorting on
Graph#1427 - Insertion
- Iterator
- Naming authority
- [IR] Enhanced name authority #1535
- Graph input/output/initializers mutation
- Validation scenarios
- Replace subgraph with new node
- Build new graph from a list of nodes
- Drop nodes
- Insert nodes
- Double iteration
- Initialization / mutation hooks
- [IR] Support sparse tensor #1428
- Function ref in nodes (Just create new constants)
- Use
richto pretty print objects https://github.com/microsoft/onnx-rewriter/pull/282 https://github.com/microsoft/onnx-rewriter/pull/278 - Beautiful (and easy) diagnostics!
-
__repr__for (nested) graph and model -
.doctor()method for displaying beautiful and actionable analysis in terminal. Userich. -
Diagnosable: definedoctor(),diagnose() -> DiagnosticMessage,add_diagnoser,clear_diagnosers()for all entities in the graph -
Extensible diagnostics with ahttps://github.com/justinchuby/onnx-doctorDiagnoser(<-naming?) class - Things we can produce diagnostics for:
- Data structure coherency: loops, nodes that do not have an owning graph, etc.
- Spec violation: Mismatched types, unknown shape/type inputs/outputs, features unsupported by the IR version, mixed opsets etc. Create error codes and reference pages for checker errors onnx/onnx#6082
- Optimization opportunities: We can make all optimize and rewrite rules diagnosers: constant foldable, detangling nodes, redundant nodes etc.
The onnx.checker can be adapted as a diagnoser
- Tools can use
diagnose()to get messages programmatically and produce reports if they want- For example, the interested can build a linter out of this.
But that's too much work for now.
- For example, the interested can build a linter out of this.
-
- Use the metastore for symbolic shape inference
- Analysis interface? onnx shape inference as an analyzer?
- Creative use of meta
- Profiling results
- Node grouping
- Integration IR Integration plan #1384
- Version converters
- Opset version converter
- IR version converter / checker
- [IR] Flatbuffer support #1429
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
