black-forest-labs/FLUX.1-dev
Text-to-Image
ā¢
Updated
ā¢
1.28M
ā¢
ā¢
8.08k
Jiannan Huang
Rbrq
Ā·
AI & ML interests
None yet
Recent Activity
liked
a model
8 days ago
black-forest-labs/FLUX.1-dev
liked
a Space
2 months ago
amirgame197/Image-to-Drawing
liked
a model
4 months ago
Qwen/Qwen2-VL-2B-Instruct
Organizations
None yet
Rbrq's activity
liked
a
model
8 days ago
liked
a
Space
2 months ago
liked
a
model
4 months ago
liked
a
Space
4 months ago
liked
a
model
4 months ago
liked
a
dataset
5 months ago
upvoted
a
paper
5 months ago
upvoted
an
article
5 months ago
Article
MobileNet Baselines
By
ā¢
ā¢
23
liked
a
model
5 months ago
updated
a
model
6 months ago
reacted to
merve's
post with š„
6 months ago
Post
5085
Real-time DEtection Transformer (RT-DETR) landed in transformers š¤© with Apache 2.0 license š
š models: https://huggingface.co/PekingU
š demo: merve/RT-DETR-tracking-coco
š paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
š 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 š„²
Transformer-based models on the other hand are computationally not as efficient š„²
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. š¤©
š models: https://huggingface.co/PekingU
š demo: merve/RT-DETR-tracking-coco
š paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
š 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 š„²
Transformer-based models on the other hand are computationally not as efficient š„²
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. š¤©
updated
a
model
6 months ago
upvoted
2
papers
7 months ago
authored
a
paper
7 months ago
liked
a
dataset
9 months ago
liked
a
model
about 1 year ago
liked
a
Space
about 1 year ago
updated
a
model
about 1 year ago
updated
a
model
over 1 year ago