search

johko / computer-vision-course

This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord
MIT License
372 stars 123 forks source link

Unit 3 - Vision Transformers - Swin.ipynb #120

Closed klyap closed 6 months ago

klyap commented 6 months ago

Notebook for Swin transformer to accompany Unit 3 - Vision Transformers - Swin.mdx

https://github.com/johko/computer-vision-course/pull/116

review-notebook-app[bot] commented 6 months ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

merveenoyan commented 6 months ago

@klyap hello! What we meant with code was that people put a model implementation (e.g. low level details like stacking layers inside the markdown file) and the notebook. We'll approve this PR, will you be able to implement the code? You can check out e.g. DETR section for example

klyap commented 6 months ago

@klyap hello! What we meant with code was that people put a model implementation (e.g. low level details like stacking layers inside the markdown file) and the notebook. We'll approve this PR, will you be able to implement the code? You can check out e.g. DETR section for example

Hi @merveenoyan ! Yep I can add the low level implementation. I looked at the DETR example and it looks like its doing an object recognition task (not low level details) in the associated notebook, and the low level implementation in the .mdx file. Should I follow suit? Or did you want low level model implementation in both .mdx and .ipynb?

merveenoyan commented 6 months ago

@klyap yes, you can just do a high-level one just to show how architecture is implemented

klyap commented 6 months ago

@klyap yes, you can just do a high-level one just to show how architecture is implemented

Ok! Added this to the .mdx file: https://github.com/johko/computer-vision-course/pull/144#discussion_r1437294826