Dataset
Visão Computacional
NVEagle/LocateAnything-Data
Dataset em destaque no Hugging Face — 27.8 mil downloads. LocateAnything-Data 中文 · Paper · Model · Code Overview LocateAnything-Data is the public training-data release for LocateAnything: Fast and Hig…
Hugging Face · Datasets
·NVEagle
·
·↓ 27778
·♥ 24
O dataset NVEagle/LocateAnything-Data está entre os destaques do Hugging Face — dados que alimentam o treinamento e a avaliação dos modelos do momento.
Ficha do dataset
- Tarefas: detecção de objetos
- Formato/modalidade: WebDataset
- Downloads: 27.8 mil · Curtidas: 24
Sobre o dataset
LocateAnything-Data 中文 · Paper · Model · Code Overview LocateAnything-Data is the public training-data release for LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding.
Como carregar
Use a biblioteca datasets do Hugging Face:
pip install -U datasets
from datasets import load_dataset
ds = load_dataset("NVEagle/LocateAnything-Data")
print(ds)
print(ds["train"][0])Tags
object-detection visual-grounding pointing document-layout-analysis gui-grounding megatron-energon webdataset multimodal
// relacionados
Leia também
Blog
Do Medical Foundation Models Generalize on the African Brain?
Blog
A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging
Blog
RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning
Blog