Results for “pytorch-geometric”

Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.

Build and train graph neural networks for drug discovery, protein modeling, and molecular science using PyTorch-native tools.

Computes the Receiver Operating Characteristic (ROC) metric using torchmetrics, supporting binary, multiclass, and multilabel tasks.

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Extends pandas for geospatial vector data operations including reading/writing shapefiles, GeoJSON, and GeoPackage, performing spatial joins, coordinate transformations, and creating static or interactive maps.

SQLAlchemy Python SQL toolkit and ORM with powerful query builder, relationship mapping, and database migrations via Alembic

Compute the F1Score metric using torchmetrics when predictions and ground-truth labels are available.