「onnx」の検索結果

Expert knowledge for Azure AI Custom Vision development including best practices, decision making, limits & quotas, security, integrations & coding patterns, and deployment. Use when exporting Custom Vision models, calling prediction APIs, using ONNX/TensorFlow, managing CMK/RBAC, or Smart Labeler, and other Azure AI Custom Vision related development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI services (use microsoft-foundry-tools), Azure Machine Learning (use azure-machine-learning), Azure AI Foundry Local (use microsoft-foundry-local).

日本語の概要は準備中です。原文の説明を表示しています。

Routes FCOS object-detection repo tasks for inference demos, config/data setup, training/evaluation, ONNX export, and legacy PyTorch internals.

日本語の概要は準備中です。原文の説明を表示しています。

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

日本語の概要は準備中です。原文の説明を表示しています。

Operate AnyLabeling desktop annotation, auto-labeling model, dataset export, install, packaging, and release workflows for the PyQt6/ONNX image-labeling package.

日本語の概要は準備中です。原文の説明を表示しています。

Route AIMET install, PyTorch/ONNX quantization, GenAILab, model access, cluster/Pod, Qualcomm SDK, optimization, export, and repository tasks to focused operating guidance.

日本語の概要は準備中です。原文の説明を表示しています。

优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供 model inference performance optimization 的脱敏案例。纯 API 调用、提示词或 token 用量优化，以及电脑卡顿，不进入本技能的模型推理实验流程。

日本語の概要は準備中です。原文の説明を表示しています。

Transcribe local audio or video with Volcengine Doubao file ASR, including BigASR 1.0 Turbo direct upload and asynchronous 1.0 standard, 1.0 idle, or 2.0 standard jobs through TOS. Use when the user asks for 火山引擎、豆包语音、录音文件识别、音视频转文字、录音稿或字幕。作为 `lecture-to-md` 的可选云端 ASR 子 skill；默认走本地 sherpa-onnx X-ASR，仅在用户明确要求云端 API 或需更高准确率时启用。

日本語の概要は準備中です。原文の説明を表示しています。

把本地长视频/音频转写成文字稿 + 可选字幕，纯本地（不上传云端），用 sherpa-onnx X-ASR Zipformer transducer 模型（int8 量化、中英双语、自动标点）。已在 macOS Apple Silicon（int8 + AMX，~100× 实时）、Linux ARM64（CPU，~32× 实时）与 Windows（PowerShell 5.1，CPU）端到端验证。使用 `$lecture-to-md` 默认 ASR 后端；默认不要换成 Qwen。

日本語の概要は準備中です。原文の説明を表示しています。

Think and work like an expert Edge / Embedded AI Engineer. Use when a task calls for Edge / Embedded AI Engineer judgment. Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates—treating train–serve preprocessing skew, float thresholds on quantized outputs, and NPU operator fallback as first-class failure modes.

日本語の概要は準備中です。原文の説明を表示しています。

Local and self-hosted text-to-speech with Kokoro, the ~82M-parameter open-weight (Apache 2.0) model by hexgrad. Use when synthesizing speech offline, on-device, in the browser, or on your own server without per-character API cost — for high-volume narration, audiobooks, privacy-constrained pipelines, and prototyping. Covers running Kokoro via the Python `kokoro` package, ONNX / kokoro-js in the browser, and the OpenAI-compatible Kokoro-FastAPI wrapper; picking voices and language codes; blending voices; chunking long text; controlling pronunciation via misaki/espeak-ng; and judging when Kokoro is the right tool versus when its lack of voice cloning, narrow emotional range, and weaker non-English quality mean you should reach for a hosted or larger model instead. Not for voice cloning, expressive/emotional character performance, or high-fidelity multilingual work — say so and route elsewhere.

日本語の概要は準備中です。原文の説明を表示しています。

Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1) MathWorks-native or 3P-imported models rebuilt as dlnetwork for lean hardware (Cortex-M, DSP), (2) direct C/C++ code generation from PyTorch and LiteRT models for high-performance hardware (Cortex-A, x86, GPU). Trigger when: user wants to deploy AI to embedded targets; generate C/CUDA from neural networks; compress AI models for MCU/DSP; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, importNetworkFromPyTorch, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.

日本語の概要は準備中です。原文の説明を表示しています。

Use when reducing model size, improving inference speed, or deploying to edge devices - covers quantization, pruning, knowledge distillation, ONNX export, and TensorRT optimizationUse when ", " mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Use when writing or changing PyTorch code — model, Dataset/DataLoader, training and evaluation loops, determinism, mixed precision, torch.compile, checkpoints with safetensors, Hugging Face models, ONNX export, and tests that run on CPU

日本語の概要は準備中です。原文の説明を表示しています。

Expert guide for Local Small Language Models (SLMs) and Edge AI execution — WebLLM, Transformers.js v3, ONNX Runtime Web, WebGPU, and zero-latency local embeddings / Panduan ahli SLM lokal dan AI edge di browser.

日本語の概要は準備中です。原文の説明を表示しています。

Generate 3D models from text or images via 5 providers: Meshy (text-to-3D, texturing, batch), fal.ai Hunyuan3D Pro ($0.225, PBR), WaveSpeedAI Rapid ($0.0225, bulk), Trellis 2 (poly control), and Local Depth (free offline ONNX depth maps + mesh). Includes GLB viewer. Triggers on 3D model, image to 3D, GLB, depth map, text to 3D, texturing, 3D asset, Meshy, Hunyuan.

日本語の概要は準備中です。原文の説明を表示しています。

Treino Ultralytics YOLO pose para keypoints do campo de futebol (32 kp), export ONNX, e inferência em vídeo com vaila.soccerfield_keypoints_ai (CSV getpixelvideo + overlay). Use quando o usuário fala em football pitch keypoints, YOLO26 pose, treino Roboflow/HF dataset martinjolif, field_keypoints_getpixelvideo, calibração FIFA, ou soccerfield_keypoints_ai.

日本語の概要は準備中です。原文の説明を表示しています。

Store and semantically search agent memory with ONNX vector embeddings on a ruOS desktop, using the Ruflo CLI. Use to persist patterns/decisions across sessions and recall them by meaning rather than exact key.

日本語の概要は準備中です。原文の説明を表示しています。

Distributed machine learning, data mining, and iterative HPC with Exasol. Covers end-to-end ML pipelines (DISTRIBUTE BY + SET scripts + BucketFS), per-entity federated training with partial_fit and ctx.reset(), batch inference, map-reduce ensemble training, distributed ensemble and SON algorithm for frequent itemset mining (Apriori, FP-Growth, association rules, market-basket analysis), Lua execute script orchestration for iterative algorithms (k-means, SGD, gradient descent), scikit-learn model training, parallel hyperparameter search, per-entity forecasting, anomaly detection, model lifecycle in BucketFS (pickle/joblib/ONNX versioning), GPU acceleration via CUDA SLCs (PyTorch/TensorFlow/RAPIDS), and ML-specific performance tuning (skew, OOM, multi-pass chunking).

日本語の概要は準備中です。原文の説明を表示しています。

NVIDIA DeepStream model-import guidance for bringing vision models from Hugging Face or NVIDIA NGC into DeepStream pipelines with export, TensorRT build, and benchmark steps.

日本語の概要は準備中です。原文の説明を表示しています。

Build kokoro-js-jp and run its real-browser e2e suite (Worker + WASM openjtalkjs g2p + ONNX kokoro-js synthesis, English and Japanese). Use when asked to verify this package actually works in a browser, to check whether a change broke synthesis, or to add browser-level regression coverage for a bug in the g2p/synthesis pipeline that vitest's pure-function tests can't catch. Not for typecheck/lint/unit-test requests — use npm run typecheck / npm test for those.

日本語の概要は準備中です。原文の説明を表示しています。