added image classification using transformer feature notebook #689
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
I have added a pynb which contains inference code for image classification using transformer. The pipeline provides a checkpoint which can be downloaded and used for adding new classes and fine tuning, a test image and the a json file of ImageNet classes. The user need not worry about the required files. The code downloads all the required file from my S3 bucket. This is a pulg-and-play notebook.
This change is required as an issue is raised to include an image classification model which utilises transformer.
This is the issue #raied:
**[FEATURE_REQUEST] Add vision transformers model to image classification #678 **
Related Issues
[FEATURE_REQUEST] Add vision transformers model to image classification #678
https://github.com/microsoft/computervision-recipes/issues/678
Checklist:
staging
and notmaster
.staging
and notmaster
.staging
.