High performance: close to roofline fp16 TensorCore (NVIDIA GPU) / MatrixCore (AMD GPU) performance on major models, including ResNet, MaskRCNN, BERT, VisionTransformer, Stable Diffusion, etc. Unified ...
Official implementation of the following papers. [1] Zhuang, Huiping, et al. "ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results