tencent/Hunyuan3D-2.1
Image-to-3D
•
Updated
•
33.8k
•
454
Yunus Dede PRO
ysdede
AI & ML interests
Passionate about audio dataset creation, labeling, and cleaning for domain-specific ASR in healthcare, specializing in fine-tuning models, real-time processing, and ASR error correction using LLMs.
Recent Activity
liked
a model
11 days ago
tencent/Hunyuan3D-2.1
liked
a model
14 days ago
inclusionAI/Ming-Lite-Omni
new activity
about 1 month ago
ysdede/webgpu-whisper-dictation:Seem amazing, please fix mobile ui
Organizations
liked
a
model
11 days ago
liked
a
model
14 days ago
Seem amazing, please fix mobile ui
1
#1 opened about 1 month ago
by
WJ88
liked
a
Space
about 1 month ago
liked
3
models
about 1 month ago
updated
a
dataset
about 1 month ago
upvoted
a
collection
about 1 month ago
liked
a
model
about 1 month ago
liked
a
Space
about 1 month ago
liked
a
model
about 1 month ago
liked
a
Space
about 2 months ago
liked
3
models
about 2 months ago
reacted to
merve's
post with 🚀
about 2 months ago
Post
6599
A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥
D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩
> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352
Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩
Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️
D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩
Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️
this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.
D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩
> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352
Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩
Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️
D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩
Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️
this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.
- 2 replies
liked
a
model
about 2 months ago
updated
a
model
2 months ago