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
[Question] The project is failing 90% of the time because of new challenges #965
Comments
Nevermind I see the workflow collecting captcha files and I also saw this project https://github.com/beiyuouo/hcaptcha-model-factory for automatic model creation, so why is this not a part of the workflow. Maybe we can use GPT for classifieng which classes are "yes" or "bad" @beiyuouo . What do you guys think? |
You can perform the zero-shot image binary classification task by modifying the modelhub instance variable. You don't need to train the model yourself. CLIP can already handle all image classification tasks. |
I've tried it but it doesn't work well. Can you show me an example using it with "Click on the animals that don't walk" |
I found why. There's an error in your code components/common.py L55 Should be "ket in label" not "label in ket" |
@QIN2DIM I opened a pull request. Please merge |
For CLIP, I have not provided a better reference case. For CLIP prompt,I offer two trigger options. I plan to use clip_candidates to handle nested types of image binary classification tasks, i.e., challenges where the prompt is invariant but the positive sample can be constantly updated. |
There are still some issues with |
The default is to use the RESNET-50 model, which is behind the times in terms of inference performance. I will write a script later to determine if current hardware resources can run a better performing CLIP model. |
hcaptcha-challenger/hcaptcha_challenger/onnx/modelhub.py Lines 295 to 308 in d5fa70a
|
I have managed to get |
You're right. That's what I want to do.
I have provided a The current data structure for |
hcaptcha-challenger/src/objects.yaml Line 6 in d5fa70a
hcaptcha-challenger/src/objects.yaml Line 736 in d5fa70a
|
@QIN2DIM PR has been approved but it still hasn't been updated on pypi |
Updated Actually, I rewrote clip_candidates about two weeks ago and also solved the current issue. However, that feature needs more testing, and I have been too busy recently. |
It's failing atm in every challenge :( |
Can you explain how to train new models because it's not visible anywhere? Maybe a small tutorial with examples would help a lot and many developers are going to be able to contribute to your project.
The text was updated successfully, but these errors were encountered: