Machine LearningConvolutional Neural NetworksOn this pageConvolutional Neural NetworksContrastive Pretraining for CNNsGitHub - keyu-tian/SparK: [ICLR'23 Spotlight] The first successful BERT-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"Fast TrainingGitHub - tysam-code/hlb-CIFAR10: Train to 94% on CIFAR-10 in less than 10 seconds on a single A100, the current world record. Or ~95.77% in ~188 seconds.