Automated Data Labeling Using Florence-2

Florence-2, a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks.
GitHub: github.com/Aar...
Try out the Florence-2 model here: huggingface.co....
Paper: arxiv.org/pdf/...
Florence-2 is pre-trained on our FLD-5B dataset encompassing a total of 5.4B comprehensive annotations across 126M images.
#computervision #largelanguagemodels #languagemodels #microsoft #ai #artificialintelligence

[@mohammadyahya78]

Amazing as usual. Been watching you for over a year

[@CodeWithAarohi]

Wow, thanks!

[@pandian1537]

We need to train Florence-2 model ocr task for custom dataset is it possible train without affecting the performance of the model so can you give some idea about this?

[@CodeWithAarohi]

Yes, you can fine tune the model on your custom dataset. I can't say anything about "affecting the performance" Try to use good quality and good quantity of data then model performance will not decrease.

[@pandian1537]

TQ so much for your reply

[@rajmeetsingh1625]

Thanks for sharing. Any video related to the custom dataset using VLM ....

[@CodeWithAarohi]

Will upload soon

[@abhishekpawar921]

Good examples. Nicely done👏🏻

[@CodeWithAarohi]

Thank you! 😃

[@billzoaiken]

Any chance you'll be doing a demo for fine-tuning? In the next couple of weeks, I'll definitely be doing some fine-tuning for custom tasks (i.e., given this image and a prompt, determine whatever), but I'm not particularly familiar with DocVQA's format, which is what the HuggingFace article uses. I would greatly appreciate a high-level overview and options in the meantime, if you have the time. Thanks for this though!

[@CodeWithAarohi]

@@billzoaiken Yes, I will make a video in day or 2. Working on it :)

[@billzoaiken]

@@CodeWithAarohi Fantastic! Your videos always serve as a great jumping-off point. Thank you!

[@dineshkumare1750]

how it is compared to qwen-vl ?

[@NakulMali-j6d]

Hell mam Thanks for your all videos and efforts. I am following your channel, but I request you please upload one detail video on how to finetune Yolov5 model for custome images classification.

[@CodeWithAarohi]

Sure

[@aneerimmco]

helpful information

[@CodeWithAarohi]

Glad it was helpful!

[@karimcherhabil8788]

Can you explain Vision mamba

[@CodeWithAarohi]

I will try