Model Analysis Python Packages

bnnr

XAI-driven augmentation & diagnostics for PyTorch vision - find model failures, fix with saliency-guided augmentation (ICD/AICD), prove with auditable reports.

cerium-delta

Real-time neural network observability platform for monitoring activations, gradients, information flow, and architecture health.

hyperview

HyperView curates datasets and provides model introspection in hyperbolic and Euclidean geometries.

prism

An alternative to MCMC for rapid analysis of models

deepdataspace

The Go-To Choice for CV Data Visualization, Annotation, and Model Analysis.

torchmeter

TorchMeter⏲️: Your all-in-one tool for Pytorch model analysis, measuring Params, FLOPs/MACs(aka. MACC or MADD), Memory cost, Inference time and Throughput! ! 🚀

pycalibrate

pycalibrate is a Python library to visually analyze model calibration in Jupyter Notebooks

modelsig

Compare LLM architectures without downloading weights — structural fingerprint & proxy-test advisor for vLLM, TensorRT-LLM, SGLang, ONNX Runtime