Hugging Face's logo
Radamés Ajna's picture
TFLOPS icon 87.8 TFLOPS
537 165 1094

Radamés Ajna

radames
Ahmad1993aj's profile picture skirano's profile picture mac4071's profile picture
·
https://observablehq.com/@radames

AI & ML interests

None yet

Recent Activity

liked a model 7 days ago
InstantX/FLUX.1-dev-IP-Adapter
liked a model 7 days ago
black-forest-labs/FLUX.1-Fill-dev
liked a model 7 days ago
black-forest-labs/FLUX.1-Redux-dev
View all activity

Articles

Organizations

Spaces-explorers's profile picture CVPR Demo Track's profile picture MONAI's profile picture Gradio-Blocks-Party's profile picture Webhooks Explorers (BETA)'s profile picture Open Access AI Collective's profile picture The Team Ten's profile picture Open-Source AI Meetup's profile picture mangoes AI's profile picture Stable Diffusion concepts library's profile picture Stable Diffusion Dreambooth Concepts Library's profile picture Daily's profile picture DragGan's profile picture meta-private's profile picture temp-org's profile picture Blog-explorers's profile picture Editing Images's profile picture leditsplusplus's profile picture sci-blender's profile picture Lilac AI's profile picture Latent Consistency's profile picture rtemp's profile picture ZeroGPU Explorers's profile picture cvmistralhackathon's profile picture Shizuku's profile picture Journalists on Hugging Face's profile picture Hugging Face - Visual Blocks's profile picture Social Post Explorers's profile picture +RAIN film festival's profile picture

radames's activity

liked 3 models 7 days ago
liked a model 8 days ago
liked a Space 8 days ago
updated a Space 10 days ago
New activity in microsoft/Florence-2-large 10 days ago

Trying to get bounding box confidence values for object detection

3
#55 opened 4 months ago by AHuaw
upvoted a paper 13 days ago
liked a model 13 days ago
liked a Space 13 days ago
New activity in microsoft/Florence-2-large 16 days ago

Segment multiple same objects in the Image

1
#18 opened 5 months ago by moaabid
Reacted to ucsahin's post with 🔥🚀 16 days ago
view post
Post
3628
Florence-2 has a great capability of detecting various objects in a zero-shot setting with the task prompt "<OD>". However, if you want to detect specific objects that the base model is not able to in its current form, you can easily finetune it for this particular task. Below I show how to finetune the model to detect tables in a given image, but a similar process can be applied to detect any objects. Thanks to @andito , @merve , and @SkalskiP for sharing the fix for finetuning the Florence-2 model. Please also check their great blog post at https://huggingface.co/blog/finetune-florence2.

Colab notebook: https://colab.research.google.com/drive/1Y8GVjwzBIgfmfD3ZypDX5H1JA_VG0YDL?usp=sharing
Finetuned model: ucsahin/Florence-2-large-TableDetection
·
liked 2 models 17 days ago
upvoted a collection 17 days ago
liked a model 22 days ago
liked 2 Spaces 22 days ago
liked a model 22 days ago