Skip to content
Other

AIWorker Arm Segmentation v1

сегментация рук робота на SAM3

2 min read

AIWorker-Arm-Segmentation-v1 — файнтюн на базе facebook/sam3 от автора Dongkkka. Модель сегментирует видимые руки, кисти, захваты, пальцы и закреплённые камеры записывающего робота AI Worker на RGB-снимках с головной и наручных камер и выдаёт instance-маски, bounding boxes и scores.

Ключевые особенности

  • Базируется на facebook/sam3; задача — mask-generation, библиотека sam3.
  • Возвращает instance-маски, bounding boxes и scores для найденных областей.
  • Работает с RGB-изображениями с головной и наручных камер робота.
  • Быстрый запуск: BF16 CUDA GPU, Python 3.12; протестировано на PyTorch 2.10, CUDA 12.8 и GPU 8 ГБ.
  • Скрипт predict.py сохраняет mask.png (union-маска в нативном разрешении) и instances.npz с masks, boxes_xyxy и scores.
  • Ограничения: дальние части рук могут пропускаться, а фон или другие роботы — иногда попадать в маску.

Пример

pip install torch==2.10.0 torchvision==0.25.0 --index-url https://download.pytorch.org/whl/cu128
pip install huggingface_hub
hf download Dongkkka/AIWorker-Arm-Segmentation-v1 --include requirements.txt predict.py inference_config.json --local-dir aiworker-arm
pip install -r aiworker-arm/requirements.txt
python aiworker-arm/predict.py input.jpg --output-dir prediction
ПодробнееОценка: 1 317 изображений для разработки; референсы автоматические/AI-assisted, не независимый человеческий ground truth.
Железо: BF16 CUDA GPU, Python 3.12; тестировали PyTorch 2.10, CUDA 12.8 и GPU на 8 ГБ.
Ограничения: дальние части рук могут пропускаться; фон или другие роботы иногда выбираются; люди, другие роботы и объекты в руках — не целевые.
Обучение: файнтюн на изображениях робота AI Worker; лицензия SAM License, производная от Meta SAM3.
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 3.2 GB · ready files4.0 GB
  • FP8 / INT8recommendedweights 1.6 GB2.3 GB
  • 4-bitweights 0.9 GB1.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Dongkkka/AIWorker-Arm-Segmentation-v1
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Dongkkka/AIWorker-Arm-Segmentation-v1 --local-dir ~/models/AIWorker-Arm-Segmentation-v1
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of sam3 (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 5All on Hugging Face
Merges 1All on Hugging Face

About the model

Dongkkka/AIWorker-Arm-Segmentation-v1
Author
Dongkkka
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments