There are no reviews yet. Be the first to send feedback to the community and the maintainers!
OpenDiT
OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and InferenceNeural-Network-Diffusion
We introduce a novel approach for parameter generation, named neural network diffusion (\textbf{p-diff}, p stands for parameter), which employs a standard latent diffusion model to synthesize a new set of parametersInfoBatch
Lossless Training Speed Up by Unbiased Dynamic Data PruningDATM
ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory MatchingLARS-ImageNet-PyTorch
Accuracy 77%. Large batch deep learning optimizer LARS for ImageNet with PyTorch and ResNet, using Horovod for distribution. Optional accumulated gradient and NVIDIA DALI dataloader.oh-my-server
Dynamic-Tuning
The official implementation of "2024Arxiv Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"GEOM
Pytorch implementation of "Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching"pytorch-lamb
PyTorch implementation of LAMB for ImageNet/ResNet-50 trainingHelen
The official implementation of "Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization"Love Open Source and this site? Check out how you can help us