daily_review
Collection
28 items
•
Updated
Feng Ji
talkative
·
AI & ML interests
large models and its applications
Recent Activity
updated
a collection
13 days ago
daily_review
updated
a collection
24 days ago
daily_review
liked
a model
4 months ago
speechbrain/sepformer-libri2mix
Organizations
None yet
talkative's activity
updated
a
collection
13 days ago
updated
a
collection
24 days ago
liked
a
model
4 months ago
liked
a
model
5 months ago
liked
a
dataset
6 months ago
updated
a
collection
7 months ago
liked
a
Space
7 months ago
reacted to
merve's
post with 👍
7 months ago
Post
5093
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. 🤩
updated
a
collection
7 months ago
updated
2
collections
9 months ago
liked
a
model
10 months ago
updated
a
Space
10 months ago
updated
a
collection
12 months ago