Add support for determnisitc seed in RandomUniform on ONNX imports
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
TensorRT currently ignores the "seed" field in RandomUniform or RandomNormal ONNX operations. A nondeterministic random seed is used every time a TensorRT engine is rebuild.
It would be nice to have a way to set the seed for random tensors from the outside like it's the case with PyTorch and NumPy for example.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at onnxOpImporters.cpp around line 4488 and inspect how RandomUniform and RandomNormal imports handle the ONNX seed field. Trace how TensorRT engines are rebuilt and how an external seed could be supplied, then define validation that repeated builds produce deterministic random tensors when a seed is set.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100