Inconsistency in inception_v3 'transform_input' default value
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
In the comments of inception_v3 it is said that the default value of transform_input is False:
https://github.com/pytorch/vision/blob/d2c763e14efe57e4bf3ebf916ec243ce8ce3315c/torchvision/models/inception.py#L42-L43
However, the default value is actually set to True when pretrained is true:
https://github.com/pytorch/vision/blob/d2c763e14efe57e4bf3ebf916ec243ce8ce3315c/torchvision/models/inception.py#L45-L47
This change is not mentioned in the source code comments or the official documentation. Sometimes people don't want the input to be transformed in the exact same way as transform_input did even when using pretrained model, or people just don't notice that transform_input is set to true when pretrained is enabled. Maybe it would be better to mention this change of default value of transform_input in the comments?
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
Read the inception_v3 comments and implementation in torchvision/models/inception.py at the referenced lines, then compare them with the official Inception v3 documentation. Done means the documented default behavior, including the change when pretrained is enabled, is stated consistently in the source comments and official documentation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, documentation
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 45/100