Downloads · 30 days
9
43% of all-time downloads
charlesH777/grasp-anything-joint-2500
grasp-anything-joint-2500 is a image-text-to-text model from charlesH777. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
基于 NVIDIA LocateAnything-3B 的语言引导二维抓取模型,joint 联合训练产物。单 checkpoint 同时支持 graspcontact 和 grasprect 两种任务。
Downloads · 30 days
9
43% of all-time downloads
All-time downloads
21
Public
Parameters
3.6B
7.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.8 GB · 100%
From the Hugging Face model README
基于 NVIDIA LocateAnything-3B 的语言引导二维抓取模型,joint 联合训练产物。单 checkpoint 同时支持 grasp_contact 和 grasp_rect 两种任务。
grasp_contact + grasp_rect 联合 — 单 checkpoint 双任务,共享 LLM backbone。
(x1, y1, x2, y2)(cx, cy, θ, width)| Split | n | gAcc_corrected_strict | mIoU_strict | center_err_median (px) |
|---|---|---|---|---|
| seen | 243 | 61.73% | 55.07% | 11.11 |
| similar | 226 | 53.10% | 46.85% | 15.00 |
| novel | 164 | 26.83% | 25.93% | 25.36 |
evaluate_realvlg_contact.py,fast 模式from locate_anything_service.model import LocateAnythingRuntime
from locate_anything_service.config import Settings
# joint checkpoint 两种模式都能跑
settings = Settings(model_id="charlesH777/grasp-anything-joint-2500")
runtime = LocateAnythingRuntime(settings)
# contact 任务
result = runtime.predict("image.jpg", "抓取红色杯子", mode="grasp_contact")
# rect 任务
result = runtime.predict("image.jpg", "抓取红色杯子", mode="grasp_rect")