Add unit 5 #7
Add unit 5 #7
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
units/en/conclusion/conclusion.mdx
Outdated
| To receive updates as the course releases, sign up for the course mailing list [here](https://mailchi.mp/911880bcff7d/ml-for-3d-course). | ||
| This has been a high-level overview of what's going on at the intersection of Machine Learning and 3D. For further exploration: | ||
|
|
||
| - Keep up with [3D Arena](https://huggingface.co/spaces/dylanebert/3d-arena) for the latest projects. |
There was a problem hiding this comment.
Could be cool to add a Hub URL with tag tracking all the open models as well for example: https://huggingface.co/models?pipeline_tag=image-to-3d&sort=trending
|
|
||
|  | ||
|
|
||
| As the field evolves rapidly, it's easy to get overwhelmed. Stay tuned for more accessible tools and resources as these projects mature. |
There was a problem hiding this comment.
Is there a Discord channel/ track where people can discuss the course, we can link that here, we did this with audio course and people still use it to discuss things.
| - Reference your model URL in the space README. | ||
|
|
||
| When completed, fill out this [form](https://forms.gle/rQedXFktHPYeikrt6) to receive your certificate. | ||
|
|
There was a problem hiding this comment.
If we can give an explicit reference example or two here so that people can try it out, note: a lot of people would do what you show here i.e. the minimum requirements so it's good to leave it just enough open-ended that there's some creativity but not too open-ended in the sense that they take the easiest way out.
There was a problem hiding this comment.
So a good example would be to make a pipeline with text to image to 3D or other things where people can sequentially stack a couple of different models/APIs together.
| - Clone and existing open-source model and change the demo experience. | ||
| - Directly clone an open-source model and demo. | ||
|
|
||
| Check out [3D Arena](https://huggingface.co/spaces/dylanebert/3d-arena) for the latest image-to-3D demos to use as starting points. |
There was a problem hiding this comment.
Same as above, some examples or just a list of ideas would be quite helpful.
units/en/unit5/run-in-notebook.mdx
Outdated
|
|
||
| import gradio as gr | ||
| import numpy as np | ||
| import spaces |
There was a problem hiding this comment.
Do we need this dependency? we can simplify this without the spaces package stuff (so that people focus on the space instead of black magic packages)
|
|
||
| Define the run function that takes an image and returns a ply file. | ||
|
|
||
| 1. Convert the image to a numpy array and normalize it to [0, 1]. |
There was a problem hiding this comment.
Noob question: Why do we normalise? (might be good to add an explanation)
| allow_duplication=True, | ||
| ) | ||
| demo.queue().launch() | ||
| ``` |
There was a problem hiding this comment.
Could we add a screenshot of how the demo would look like?
|
|
||
| The instructions below are tested on an RTX 4090 on WSL2 Ubuntu 22.04. Instructions will differ and may not work, depending on your setup. | ||
|
|
||
| 1. Install `git`, `python 3.10`, and `cuda` if not already installed. |
There was a problem hiding this comment.
Curious q: does this work locally on mac?
Note: people can also run the space via docker locally: https://huggingface.co/docs/hub/en/spaces-run-with-docker
Would be good to add that as an example too (it's okay to skip it if you think it's too much complexity)
| demo.queue().launch() | ||
| ``` | ||
|
|
||
| This will work on CPU, but relies on the original LGM-tiny, instead of your custom model. However, is your focus is on UI/UX or downstream tasks, this may be acceptable. |
There was a problem hiding this comment.
This is a bit counter intuitive, we use gradio_client to run the same space as another space. Maybe we can add a section above just showing the use of gradio_client? this way it'll help make it clear that they can use other models/ spaces as well.
|
|
||
| 1. **Run in this notebook**: Validate the code quickly. | ||
| 2. **Run locally**: Clone your space and run it locally. | ||
| 3. **Community grant**: Building something cool? Apply for a community GPU grant in your space settings. |
There was a problem hiding this comment.
I'd add a mention of your Hub username so that you can explicitly see/ filter the community grants if asked.
No description provided.