Is NCHW the only supported input layout for IConvolutionLayer in TensorRT?
Open
Nobody has claimed this yet.
triaged
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
I’m working with TensorRT and need to use IConvolutionLayer. I would like to know if the input tensor is required to be in NCHW format, or if it’s possible to specify a different layout such as NHWC. If custom layouts are supported, how can they be set for the layer? I’m using TensorRT version 10.2. Any clarification would be appreciated!
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 with the TensorRT 10.2 IConvolutionLayer API documentation and its input-layout behavior. Determine whether layouts such as NHWC are supported and how they are configured; done means providing a confirmed, documented answer, with any relevant API entry points identified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100