查找技能

Use Flair for NLP annotation, embeddings, text/sequence model prediction, corpus loading, training/fine-tuning, HunFlair biomedical NER/linking, and production troubleshooting.

中文简介正在准备中。当前显示原文说明。

Operate Fugue workflows, FugueSQL, backend selection, and notebook magics for pandas and distributed dataframe execution.

中文简介正在准备中。当前显示原文说明。

Operate FATE 2.2.0 federated-learning deployments, FateFlow Pipeline workflows, local launchers, and component CLI/runtime inspection.

中文简介正在准备中。当前显示原文说明。

Use FlagEmbedding for embedding, reranking, retrieval evaluation, and fine-tuning workflows.

中文简介正在准备中。当前显示原文说明。

Routes FlashText tasks for keyword extraction, replacement, fuzzy matching, keyword loading, and keyword-inspection workflows.

中文简介正在准备中。当前显示原文说明。

Foolbox operating guidance for wrapping vision models, running adversarial attacks, measuring clean and robust accuracy, handling NumPy/PyTorch/TensorFlow/JAX backends, and loading Foolbox-compatible model-zoo repositories.

中文简介正在准备中。当前显示原文说明。

Use the faster-whisper package for CTranslate2-backed Whisper transcription, model selection, CPU/CUDA setup, audio utilities, VAD, timestamps, and conversion guidance.

中文简介正在准备中。当前显示原文说明。

Guides FastVideo video, image, and audio generation, config-first inference, serving, training, distillation, evaluation, and performance workflows.

中文简介正在准备中。当前显示原文说明。

Use for Feast feature store tasks: feature repositories, definitions, CLI, retrieval, materialization, serving, RAG/vector search, integrations, and Feast contributor workflows.

中文简介正在准备中。当前显示原文说明。

Guides Fiona workflows for GDAL-backed vector data I/O, GeoJSON-like features and schemas, CRS transforms, local virtual files, cloud-session boundaries, and the fio CLI.

中文简介正在准备中。当前显示原文说明。

Operate Flash Linear Attention package workflows: setup, kernels, layers/models, KDA/context parallel, and benchmarking.

中文简介正在准备中。当前显示原文说明。

Routes face-alignment installation, import checks, landmark-detection workflows, and detector-backend selection.

中文简介正在准备中。当前显示原文说明。

Route fastdup workflows for visual dataset curation, annotation-driven analysis, embeddings and search, and video or exchange plumbing.

中文简介正在准备中。当前显示原文说明。

Route Flower repository tasks for app authoring, strategies and mods, local simulation and deployment, Flower Datasets and examples, and repository maintenance.

中文简介正在准备中。当前显示原文说明。

Use face.evoLVe for high-performance face recognition workflows across alignment, data preparation, PyTorch training, feature verification, and Paddle deployment.

中文简介正在准备中。当前显示原文说明。

Use this skill for EverOS local-first Markdown memory service setup, HTTP memory and knowledge APIs, cascade/OME operations, and observability integration.

中文简介正在准备中。当前显示原文说明。

Routes evo trajectory-evaluation workflows for APE/RPE, trajectory I/O, result analysis, configuration, and programmatic usage.

中文简介正在准备中。当前显示原文说明。

Use fastMRI for MRI reconstruction data loading, MRI operators, reconstruction models, Lightning training, evaluation, and submission preparation.

中文简介正在准备中。当前显示原文说明。

Guides Researchers through Faiss installation, dense and binary similarity search, index training and composition, persistence and evaluation, and explicitly gated CPU/GPU interoperability workflows.

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

Use FFCV to convert datasets into .beton files, build fast PyTorch loader pipelines, handle image and custom fields/transforms, and tune cache, traversal, and throughput behavior.

中文简介正在准备中。当前显示原文说明。

Create, polish, and troubleshoot figures4papers-style publication-ready matplotlib figures, including grouped bars, trends, radar charts, heatmaps, concept diagrams, manifolds, and high-DPI/vector export workflows.

中文简介正在准备中。当前显示原文说明。

Guides TensorFlow Fast Style Transfer training, image stylization, and video stylization workflows from checkpoints, VGG/COCO assets, and script-oriented CLIs.

中文简介正在准备中。当前显示原文说明。

Router for FunASR speech workflows: local transcription, subtitles, services, vLLM, normalization, and training/export.

中文简介正在准备中。当前显示原文说明。