查找技能

Guides DeepMotionEditing BVH animation, skeleton-aware motion retargeting, motion style transfer, and Blender visualization workflows for research use.

中文简介正在准备中。当前显示原文说明。

Route Torchreid deep-person-reid workflows for person re-identification training, evaluation, feature extraction, metrics, visualization, and model export.

中文简介正在准备中。当前显示原文说明。

Route DeepKE knowledge extraction workflows across supervised extraction, data prep, triples, LLMs, and MCP tools.

中文简介正在准备中。当前显示原文说明。

Route DeepSearcher workflows for provider setup, data ingestion, RAG querying, CLI and service operation, and evaluation.

中文简介正在准备中。当前显示原文说明。

Use the DeepGCNs PyTorch operating guide for graph convolution layers, dynamic and dilated KNN blocks, point-cloud classification or segmentation, PPI, OGB/DeeperGCN, and reversible memory-efficient GNN workflows.

中文简介正在准备中。当前显示原文说明。

Route and use the repository's PyTorch reinforcement-learning examples across tabular control, DQN, on-policy actor-critic, and off-policy continuous control.

中文简介正在准备中。当前显示原文说明。

Router for DeepAnalyze agentic data-science workflows.

中文简介正在准备中。当前显示原文说明。

Use DeepDanbooru for anime-style image tag estimation, project and Danbooru-style dataset preparation, TensorFlow training, image evaluation, TFLite conversion, and experimental Grad-CAM workflows.

中文简介正在准备中。当前显示原文说明。

Route DataFlow workflows for pipelines, text and document processing, serving, evaluation, and Ray acceleration.

中文简介正在准备中。当前显示原文说明。

Routes DeepStream-Yolo deployment, model conversion, multi-GIE, and INT8 workflows for supported YOLO-family models.

中文简介正在准备中。当前显示原文说明。

Route DeblurGAN users to data preparation, training, and single-image inference workflows.

中文简介正在准备中。当前显示原文说明。

Use the DataSciencePython tutorial/example collection through modern self-contained helpers for Python data-science resources, statsmodels logistic regression, scikit-learn Kaggle-style tabular classifiers, and Twitter JSONL extraction.

中文简介正在准备中。当前显示原文说明。

Use when building, debugging, testing, or maintaining Plotly Dash applications, callbacks, server backends, component packages, renderer internals, and Dash repository workflows.

中文简介正在准备中。当前显示原文说明。

Use deep-daze for CLIP-guided Siren image generation through the imagine CLI and Python APIs, with runtime inspection and troubleshooting.

中文简介正在准备中。当前显示原文说明。

Use this repo skill for Dask, the Python parallel computing library, when working with lazy task graphs, schedulers, Dask Array, Dask DataFrame, Dask Bag/bytes IO, configuration, diagnostics, CLI usage, or contributor validation.

中文简介正在准备中。当前显示原文说明。

Routes Darkflow object-detection, training, and export workflows for the legacy YOLO package.

中文简介正在准备中。当前显示原文说明。

Use the DALLE2-pytorch package for DALL-E 2 style text-to-image model APIs, diffusion prior/decoder training, WebDataset data layouts, and tracker/checkpoint workflows.

中文简介正在准备中。当前显示原文说明。

Guides agents using the datamol Python package for RDKit-first molecular IO, preparation, fingerprints, similarity, structure generation, visualization, and utility workflows.

中文简介正在准备中。当前显示原文说明。

Operate lucidrains DALLE-pytorch for DALL-E style VAE training, transformer training, generation, CLIP ranking, and backend troubleshooting.

中文简介正在准备中。当前显示原文说明。

Route D-FINE object-detection setup, training, architecture inspection, inference, export, and troubleshooting workflows.

中文简介正在准备中。当前显示原文说明。

Use this skill when working with Hugging Face Datasets: loading local or Hub datasets, defining Features schemas, processing/streaming datasets, converting formats, sharing to the Hub, managing cache/offline behavior, or using datasets-cli.

中文简介正在准备中。当前显示原文说明。

Data-Juicer repo router for local recipes, Ray recovery, and service/MCP workflows.

中文简介正在准备中。当前显示原文说明。

Router for CVNets training, evaluation, registry, data, and export workflows.

中文简介正在准备中。当前显示原文说明。

Operate CVAT for computer-vision annotation, dataset workflows, SDK/CLI automation, auto-annotation, and self-hosted deployment.

中文简介正在准备中。当前显示原文说明。