High-fidelity performance metrics for generative models in PyTorch

Count the MACs / FLOPs of your PyTorch model.

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Code for the ACL-2022 paper "Knowledge Neurons in Pretrained Transformers"