Master different vision tasks with pre-trained Florence-2 | Community Q&A (Jul 3)

Подписаться 36 тыс.

Просмотров 2,7 тыс.

50% 1

Master different vision tasks with pre-trained Florence-2 in this live coding community Q&A.
Resources:
- Roboflow: roboflow.com
- 📓 Florence notebook: colab.research.google.com/git...
- 🗞 Florence-2 arXiv paper: arxiv.org/abs/2311.06242
- 🗞 Florence-2 overview blog post: blog.roboflow.com/florence-2
- 🗞 Florence-2 fine-tuning blog post: blog.roboflow.com/fine-tune-f...
- 🔗 Florence-2 HF Space: huggingface.co/spaces/gokaygo...
Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐

Наука

Опубликовано:

2 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 16

@adiasz 13 дней назад

Great content. Thanx!

@AlbaraFawazShehadeh 26 дней назад

Great, we want tutorial how to fine tune Florence-2 for handwritten recognition task

@JV-vp5vl 25 дней назад

This RF channel & blog really are the one and only best sources of information to stay on the edge for intermediate data scientists/ml engineers with a practical approach. Ultralytics YT channel is also improving a lot lately! I

@Roboflow 24 дня назад

Thanks a lot! 🙏🏻 It so much pleasure to read comments like this.

@JV-vp5vl 22 дня назад

@@Roboflow my pleasure! Will continue to ad you among my peers.

@vinni8619 2 дня назад

great video! how can i increase the size of the labels in the image?

@Roboflow День назад

Thanks, change text_thickness and text_scale values of LabelAnnotator

@NaveenKumarLaskari 5 дней назад

How can I finetune the model for OCR_WITH_REGION task

@AlbaraFawazShehadeh 26 дней назад

Great, how to fine tune florence-2 for handwritten recognition with region tasks

@user-xs7oy8hs5t 21 день назад

Great job. I have a question. Could this model help me detect image manipulation traces, such as physical photo substitution or digital tampering like splicing, cloning, and airbrushing? Feel free to suggest any other model. Thank you

@Roboflow 21 день назад

Hi :) That unfortunately does not sound like a use case for Florence-2

@user-xs7oy8hs5t 20 дней назад

@@Roboflow Could you suggest a model that I can fine-tune for this problem?

@Alan-b8o 26 дней назад

Hey, how does one use an exported model after training is complete on colab locally? Couldn't ask during the livestream

@terranthegaint405 25 дней назад

provide the path to the saved model when loading it, use the code in the colab notebook he was showing as a reference.

@Alan-b8o 25 дней назад

@@terranthegaint405 Could you show me a snippet of what part exactly do I need to alter?

@terranthegaint405 25 дней назад

@@Alan-b8o CHECKPOINT = "microsoft/Florence-2-base-ft" REVISION = 'refs/pr/6' use the path to your model in place of "microsoft/Florence-2-base-ft" and remove REVISION and then modify model and processor to look like this model = AutoModelForCausalLM.from_pretrained(CHECKPOINT, trust_remote_code=True).to(DEVICE) processor = AutoProcessor.from_pretrained(CHECKPOINT, trust_remote_code=True)