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

How to Detect #4

Open
speedoandy opened this issue Feb 3, 2023 · 3 comments
Open

How to Detect #4

speedoandy opened this issue Feb 3, 2023 · 3 comments

Comments

@speedoandy
Copy link

Could u explain how to detect with any image?

@chadha-sridi
Copy link

Hi,
This is what I did to run it on my images:
1/First add a "configuration file" for your images in deep-darts/configs (one similar to the 2 yaml files already there)
2/Then you need annotate your images by running the annotate.py this will create the labels (you might have to put them in a specific directory: see what you get from the error message).
This will create the true "labels" for your images.
3/ make sure to comment the assert line in dataloader.py (asserts the dataset is either d1 or d2) and add a line to handle your data.
In predict.py also handle the case for your own config by setting your own value for the labels_path
4/Then you run the predict.py on your images

@Kariti
Copy link

Kariti commented Dec 26, 2024

Hello @wmcnally ,

i test on my PC (NVIDIA RTX A2000 Laptop GPU computeCapability: 8.6)

i downloads models and cropped image from dataset1
i 've launched predict dataset1 for instance with dataloader(d1_03_03_2020) and i have 0% PCS.

I'd appreciate it if you could spare me some time on discord ? i live in france on GMT +1
Thank you very much four your help

@m8rzel
Copy link

m8rzel commented Feb 10, 2025

Hey @Kariti,
did you found a solution?
Best regards
Marcel

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

4 participants