Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models
•
124
Merve Noyan PRO
merve
AI & ML interests
VLMs, vision & co
Articles
Organizations
Posts
42
Post
3618
Real-time DEtection Transformer (RT-DETR) landed in transformers 🤩 with Apache 2.0 license 😍
🔖 models: https://huggingface.co/PekingU
🔖 demo: merve/RT-DETR-tracking-coco
📝 paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
📖 notebook: https://github.com/merveenoyan/example_notebooks/blob/main/RT_DETR_Notebook.ipynb
YOLO models are known to be super fast for real-time computer vision, but they have a downside with being volatile to NMS 🥲
Transformer-based models on the other hand are computationally not as efficient 🥲
Isn't there something in between? Enter RT-DETR!
The authors combined CNN backbone, multi-stage hybrid decoder (combining convs and attn) with a transformer decoder. In the paper, authors also claim one can adjust speed by changing decoder layers without retraining altogether.
The authors find out that the model performs better in terms of speed and accuracy compared to the previous state-of-the-art. 🤩
🔖 models: https://huggingface.co/PekingU
🔖 demo: merve/RT-DETR-tracking-coco
📝 paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
📖 notebook: https://github.com/merveenoyan/example_notebooks/blob/main/RT_DETR_Notebook.ipynb
YOLO models are known to be super fast for real-time computer vision, but they have a downside with being volatile to NMS 🥲
Transformer-based models on the other hand are computationally not as efficient 🥲
Isn't there something in between? Enter RT-DETR!
The authors combined CNN backbone, multi-stage hybrid decoder (combining convs and attn) with a transformer decoder. In the paper, authors also claim one can adjust speed by changing decoder layers without retraining altogether.
The authors find out that the model performs better in terms of speed and accuracy compared to the previous state-of-the-art. 🤩
Post
2892
Just shipped: introduction to vision language models (aka image-text-to-text) https://huggingface.co/tasks/image-text-to-text
Learn about more machine learning tasks at https://huggingface.co/tasks
Learn about more machine learning tasks at https://huggingface.co/tasks
Collections
22
spaces
98
Running
on
Zero
30
🌖
RT DETR Tracking Coco
Running
on
Zero
1.04k
👨🏻🎤
ChatGPT Prompt Generator
Runtime error
35
🐨
Paligemma Tracking
Running
on
Zero
61
⚡
Owl Tracking
Powerful foundation model for zero-shot object tracking
Running
on
Zero
46
📚
Paligemma Doc
Try PaliGemma on document understanding tasks
Running
on
Zero
36
🌖
BLIP2 with transformers
BLIP2 (cutting edge image captioning) in 🤗transformers
models
75
merve/vq-vae
Updated
•
10
merve/paligemma_vqav2
Updated
•
84
•
3
merve/pg-vqav2
Updated
merve/VeCap-DFN-h14
Zero-Shot Image Classification
•
Updated
•
10
merve/VeCap-DFN-l14
Updated
merve/VeCap-DFN-b16
Zero-Shot Image Classification
•
Updated
•
11
merve/VeCLIP-b16-100m
Zero-Shot Image Classification
•
Updated
•
11
merve/VeCLIP-b16-200m
Zero-Shot Image Classification
•
Updated
•
15
•
1
merve/VeCLIP-b16-12m
Zero-Shot Image Classification
•
Updated
•
10
merve/VeCLIP-b16-3m
Zero-Shot Image Classification
•
Updated
•
11
datasets
23
merve/pascal-voc
Viewer
•
Updated
•
336k
merve/YouCook2
Viewer
•
Updated
•
2k
•
4
merve/faiss_embeddings
Updated
merve/pokemon-ds-embeddings
Viewer
•
Updated
•
833
•
3
•
4
merve/tr-h4-norobots
Updated
•
2
•
10
merve/lego_sets_latest
Viewer
•
Updated
•
61
•
4
•
1
merve/ai-tube-dummy
Updated
•
2
merve/my-blog-images
Viewer
•
Updated
•
1
•
3
•
1
merve/turkish_instructions
Viewer
•
Updated
•
51.6k
•
73
•
33
merve/ner-flags
Updated
•
2