Fixing issue #678 -> pynb for image classification using vision transformer pretrained on ImageNet.

[ShreyasJoshi7]

Description

I have added a notebook which contains inference code for image classification using vision transformer pretrained on IamgeNet. The code performs the following tasks:

1. downloads the checkpoint (which can be downloaded and used to fintune the model on aditional classes).
2. downloads a test image.
3. downloads the json file of ImageNet classes.

This notebook solves the issue #678 which requires an image classifier which uses transformer.

Related Issues

[FEATURE_REQUEST] Add vision transformers model to image classification #678

Checklist:

• [ x] I have followed the contribution guidelines and code style for this project.
• [ x] This branch is created from staging and not master.
• [ x] This PR is being made to staging and not master.
• [ x] I will squash merge this PR into staging.
• [ x] I have added tests covering my contributions.
• [ x] I have updated the documentation accordingly.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[ShreyasJoshi7]

@microsoft-github-policy-service agree

[smith-kyle]

Just a heads up, you can review these notebook changes with GitNotebooks too: https://gitnotebooks.com/microsoft/computervision-recipes/pull/690

I think it offers some advantages over what you're currently using.

[ShreyasJoshi7]

Just a heads up, you can review these notebook changes with GitNotebooks too: https://gitnotebooks.com/microsoft/computervision-recipes/pull/690

I think it offers some advantages over what you're currently using.

@smith-kyle thank you for the suggestion.

[ShreyasJoshi7]

My Amazon account expired and I had to update the S3 link.

[ShreyasJoshi7]

I am note able to find the information about the author, but can the author please merge this PR? It has passed all the checks.