pytorch / pytorch/executorch

Use real image input in demo colab notebook

Open
#8,851 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

module: examples module: user experience triaged
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

📚 The doc issue

We have a Colab notebook which we link to in the Getting Started documentation, which illustrates exporting, lowering, and running (with Pybindings) MobileNet V2. It would be nice to have it load a real image and print the top predicted classes, as opposed to current behavior of using random inputs and printing PASS. It would make a nice demo and illustrate it working end to end. It also forces us to include some of the practical bits for input transformations, matching the "real" user experience. We can also align with the content in the getting started section to ideally make them match up.

Suggest a potential alternative/fix

No response

cc @mergennachin @iseeyuan @lucylq @helunwencser @tarun292 @kimishpatel @jackzhxng @byjlw

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Open the linked Colab notebook and compare its MobileNet V2 flow with the Getting Started documentation. Replace the random input and PASS output with a real image, the required input transformations, and printed top predicted classes; done means the export, lowering, Pybindings execution, and end-to-end demo work together.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.