TheLastBen/Papercut_SDXL
Text-to-Image • Updated • 636 • • 72
Robert Seaton
bobse
AI & ML interests
all the things: astrophysics, gravitational waves, applied cryptography, machine learning, team development
Recent Activity
liked a model about 1 month ago
TheLastBen/Papercut_SDXL liked a model about 1 month ago
joachimsallstrom/aether-ghost-lora-for-sdxl liked a model about 1 month ago
Cactus-Compute/needle2Organizations
None yet
liked 3
models about 1 month ago
liked 5
models 11 months ago
Qwen/Qwen3-VL-2B-Instruct
Image-Text-to-Text • 2B • Updated • 3.1M • • 474
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 2.26M • • 3.39k
MiniMaxAI/MiniMax-M2
Text Generation • 229B • Updated • 277k • • 1.5k
bullerwins/Wan2.2-I2V-A14B-GGUF
Image-to-Video • 14B • Updated • 113k • 306
black-forest-labs/FLUX.1-Krea-dev
Text-to-Image • 12B • Updated • 57.2k • • 922
liked 4
models about 1 year ago
reacted to merve's post with ❤️ over 1 year ago
Post
6780
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 over 1 year ago
liked a
Space over 1 year ago
liked 3
models over 1 year ago
liked a
Space over 1 year ago
liked a
model over 1 year ago