New model #195
Merged
New model #195
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
I think we should not hardcode the URL in the code to better manage model's upgrade. It also means that we will have to implement the verification of the scheme as asked by Codacy |
RonanMorgan
requested changes
May 21, 2024
|
Hi @RonanMorgan , thanks for the review, I don't agree with you it's much better to hardcode the url for an easier update on all devices. If we have to chnager a .env one by one it will quickly become unmanageable if we find a you to update it automatically why not, maybe it's feasible with hugging face. But it's another PR here I just want to upgrade to model |
RonanMorgan
approved these changes
May 21, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Following our discussion on the slack vision channel, we have a new reference model that has been added to huggingface. I suggest using it from now on.
This new model uses a larger 1024x1024 image instead of 384, 640. The inference on the pi is done in 3.5s instead of 1s previously, which is not a problem especially with PR #194