deepseek-ai/DeepSeek-V3-0324
Text Generation
•
Updated
•
189k
•
•
2.52k
soulteary
soulteary
AI & ML interests
None yet
Recent Activity
liked
a model
18 days ago
deepseek-ai/DeepSeek-V3-0324
liked
a Space
7 months ago
Qwen/Qwen2.5
liked
a model
9 months ago
Alibaba-NLP/gte-Qwen2-7B-instruct
Organizations
soulteary's activity
liked
a
model
18 days ago
liked
a
Space
7 months ago
liked
2
models
9 months ago
upvoted
a
collection
9 months ago
liked
3
models
11 months ago
liked
2
models
12 months ago
liked
3
models
about 1 year ago
reacted to
SkalskiP's
post with ❤️
about 1 year ago
Post
YOLO-World: Real-Time, Zero-Shot Object Detection 🔥 🔥 🔥
YOLO-World was designed to solve a limitation of existing zero-shot object detection models: speed. Whereas other state-of-the-art models use Transformers, a powerful but typically slower architecture, YOLO-World uses the faster CNN-based YOLO architecture.
YOLO-World provides three models: small with 13M (re-parametrized 77M), medium with 29M (re-parametrized 92M), and large with 48M (re-parametrized 110M) parameters.
The YOLO-World team benchmarked the model on the LVIS dataset and measured their performance on the V100 without any performance acceleration mechanisms like quantization or TensorRT.
According to the paper, YOLO-World reached 35.4 AP with 52.0 FPS for the L version and 26.2 AP with 74.1 FPS for the S version. While the V100 is a powerful GPU, achieving such high FPS on any device is impressive.
- 🔗 YOLO-World arXiv paper: https://lnkd.in/ddRBKCCX
- 🔗 my YOLO-World technical report: https://blog.roboflow.com/what-is-yolo-world
- 🤗 YOLO-World space: SkalskiP/YOLO-World
YOLO-World was designed to solve a limitation of existing zero-shot object detection models: speed. Whereas other state-of-the-art models use Transformers, a powerful but typically slower architecture, YOLO-World uses the faster CNN-based YOLO architecture.
YOLO-World provides three models: small with 13M (re-parametrized 77M), medium with 29M (re-parametrized 92M), and large with 48M (re-parametrized 110M) parameters.
The YOLO-World team benchmarked the model on the LVIS dataset and measured their performance on the V100 without any performance acceleration mechanisms like quantization or TensorRT.
According to the paper, YOLO-World reached 35.4 AP with 52.0 FPS for the L version and 26.2 AP with 74.1 FPS for the S version. While the V100 is a powerful GPU, achieving such high FPS on any device is impressive.
- 🔗 YOLO-World arXiv paper: https://lnkd.in/ddRBKCCX
- 🔗 my YOLO-World technical report: https://blog.roboflow.com/what-is-yolo-world
- 🤗 YOLO-World space: SkalskiP/YOLO-World
liked
5
models
over 1 year ago
stabilityai/stable-video-diffusion-img2vid-xt
Image-to-Video
•
Updated
•
320k
•
3k
01-ai/Yi-34B-Chat
Text Generation
•
Updated
•
6.94k
•
350
stabilityai/sdxl-turbo
Text-to-Image
•
Updated
•
259k
•
•
2.37k
01-ai/Yi-34B
Text Generation
•
Updated
•
5.54k
•
1.3k
openai/clip-vit-base-patch16
Zero-Shot Image Classification
•
Updated
•
4.95M
•
•
116
updated
a
dataset
over 1 year ago