Skip to content
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

Predict video returns bad request #221

Open
leveesean opened this issue Jan 12, 2024 · 4 comments
Open

Predict video returns bad request #221

leveesean opened this issue Jan 12, 2024 · 4 comments

Comments

@leveesean
Copy link

I've attempted to use model.predict_video a few different ways and it yields the same result, a 400 bad request.

  1. Follow the steps in this blog
    a. Essentially use the example from cookbook and add an mp4 to the folder
  2. Follow the steps in this blog

Here's a link to my project / mode, we're on the free plan which appears to offer video inference.

https://app.roboflow.com/levee-labs-inc/hotel-model/deploy/2

Any assistance would be greatly appreciated.

Thanks,
Sean

@PacificDou
Copy link
Contributor

PacificDou commented Jan 12, 2024

Hi @leveesean , thanks for the report! We made an update to fix it. Could you please have a try again?

@leveesean
Copy link
Author

itsworking

@leveesean
Copy link
Author

Thanks for the quick assistance @PacificDou - Looks good this morning.

@leveesean
Copy link
Author

Hey @PacificDou once again appreciate the quick turnaround on fixing that last week.

Any chance we could get some sort of RCA or reassurance that this service will remain stable? Curious if this was an issue with my account specifically, or if this was an issue with the roboflow service.

For context, we're currently building out an MVP for our product and demoing to potential investors, so it's important that our product is stable during our demos. Obviously once we launch it will be critical that our product is stable too. If we can't trust that it will be stable we'll need to switch to another service.

Let me know if you'd like to take this offline, and feel free to close the issue out if you'd like.

Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants