Welcome to Community Computer Vision Course! This course is prepared and continuously improved by the community for the community 🤗
Simply head over huggingface.co/learn and start studying the chapters.
To certify that you have completed the course, we require you to finish the assignment. The assignment consists of two steps:
There are notebooks under Notebooks/Vision Transformers section. As of now, we have notebooks for object detection, image segmentation and image classification. You can either train a model on a dataset that exists on 🤗 Hub or upload a dataset to a dataset repository and train a model on that.
The model repository needs to have following:
A properly filled Model Card (you can check out here for more information https://huggingface.co/docs/hub/en/model-cards)
If you trained a model with transformers and pushed it to Hub, the model card will be generated. In that case, edit the card and fill in more details.
Add the dataset’s id to model card to link the model repository to the dataset repository.
This part of the assignment involves building a Gradio based application to your computer vision model, and sharing it on 🤗 Spaces.
You can get started with Gradio here https://huggingface.co/learn/nlp-course/chapter9/1?fw=pt#introduction-to-gradio
You can learn about how to share your application on 🤗 Spaces here https://huggingface.co/learn/nlp-course/chapter9/4?fw=pt
You need to fill the form here with your name, e-mail, and links to your model and Space repositories. https://forms.gle/JaSYEf1pEZ4HtNKGA