-
-
Notifications
You must be signed in to change notification settings - Fork 43
docs: Background segmentation #1951
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
…mentation-example
…mentation-example
|
pkg.pr.new packages benchmark commit |
|
The tiniest (and default) model of them all was left in the repo on purpose - it's good to have it locally in case of some issues with the HuggingFace |
iwoplaza
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yeppers! Works great 💜
| sampler: { sampler: 'filtering' }, | ||
| }); | ||
|
|
||
| export const cropBoundsSlot = tgpu.slot<TgpuUniform<d.Vec4f>>(); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'd recommend an accessor for this usecase instead. We don't really care that it's a uniform, rather that it's a vec4f
| export const cropBoundsSlot = tgpu.slot<TgpuUniform<d.Vec4f>>(); | |
| export const cropBoundsAccess = tgpu['~unstable'].accessor(d.vec4f); |
| export const MODEL_WIDTH = 320; | ||
| export const MODEL_HEIGHT = 320; | ||
|
|
||
| const modelCache = new Map<string, ArrayBuffer>(); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we clear the cache in example cleanup?
Introducing variety of in-house developed models and pulling them directly form hugging face.