huggingface-vision-trainer
[ 公式 ]Hugging Faceビジョントレーナースキル、Hugging Face JobsのクラウドGPUでビジョンモデルをトレーニングしてファインチューニングする
Killer-Skillsディレクトリで数千のAI Agentスキルを探索・インストール。Claude Code、Windsurf、Cursorなどに対応。
Hugging Faceビジョントレーナースキル、Hugging Face JobsのクラウドGPUでビジョンモデルをトレーニングしてファインチューニングする
On-chain AI agent generator on Base. Create, mint, and register AI agents with fully on-chain pixel art and identity — powered by ERC-8004.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and multi-platform deployment. Claude Code · Codex · Copilot · Cursor · Factory · Warp · Windsurf.
A lightweight validator monitor for the beacon chain: indexer + API + Telegram bot with a mini-app for real-time validator performance, rewards, and alerts.
Ready-to-use AI skills and human guides for documentation, git workflows, and project management. MIT licensed, zero dependencies.
Migrate existing multi-agent Discord/Slack setup to the new agent/server/category/channel context architecture. Restructures group workspaces into isolated per-channel notebooks with shared category and agent identity layers.
Use when writing TypeScript code that interacts with dependencies, handles credentials, executes child processes, or manages configuration. Provides Shai-Hulud supply chain attack countermeasures at the code level including safe dependency usage, credential handling, subprocess hardening, and runtime integrity patterns.
Configure LangChain4J vector stores for RAG applications. Use when building semantic search, integrating vector databases (PostgreSQL/pgvector, Pinecone, MongoDB, Milvus, Neo4j), implementing embedding storage/retrieval, setting up hybrid search, or optimizing vector database performance for production AI applications.
Use when writing TypeScript code that interacts with dependencies, handles credentials, executes child processes, or manages configuration. Provides Shai-Hulud supply chain attack countermeasures at the code level including safe dependency usage, credential handling, subprocess hardening, and runtime integrity patterns.
Use when writing TypeScript code that interacts with dependencies, handles credentials, executes child processes, or manages configuration. Provides Shai-Hulud supply chain attack countermeasures at the code level including safe dependency usage, credential handling, subprocess hardening, and runtime integrity patterns.
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.