NUS-HPC-AI-Lab / LARS-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.
☆38Updated 3 years ago
Alternatives and similar repositories for LARS-ImageNet-PyTorch:
Users that are interested in LARS-ImageNet-PyTorch are comparing it to the libraries listed below
- PyTorch implementation of LAMB for ImageNet/ResNet-50 training☆13Updated 3 years ago
- ☆41Updated 2 years ago
- ☆45Updated 4 years ago
- ☆200Updated last year
- ☆49Updated last year
- In progress.☆64Updated 10 months ago
- MLPruning, PyTorch, NLP, BERT, Structured Pruning☆21Updated 3 years ago
- Code for ICML 2021 submission☆35Updated 3 years ago
- ☆40Updated 3 years ago
- [ICML 2021] "Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training" by Shiwei Liu, Lu Yin, De…☆46Updated last year
- Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better perfo…☆90Updated 2 years ago
- [ICLR 2023] Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation☆12Updated last year
- Parameter Efficient Transfer Learning with Diff Pruning☆73Updated 3 years ago
- Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples [NeurIPS 2021]☆30Updated 3 years ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆109Updated last year
- [ICML 2021 Oral] "CATE: Computation-aware Neural Architecture Encoding with Transformers" by Shen Yan, Kaiqiang Song, Fei Liu, Mi Zhang☆19Updated 3 years ago
- [NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang…☆90Updated last year
- Implementation of (overlap) local SGD in Pytorch☆33Updated 4 years ago
- PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models. ICML 2021☆55Updated 3 years ago
- This project is the official implementation of our accepted ICLR 2022 paper BiBERT: Accurate Fully Binarized BERT.☆85Updated last year
- Code and checkpoints of compressed networks for the paper titled "HYDRA: Pruning Adversarially Robust Neural Networks" (NeurIPS 2020) (ht…☆90Updated 2 years ago
- [Neurips 2021] Sparse Training via Boosting Pruning Plasticity with Neuroregeneration☆31Updated last year
- This is the official PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".☆40Updated 3 years ago
- ☆43Updated last year
- [ICLR 2022] The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training by Shiwei Liu, Tianlo…☆73Updated 2 years ago
- [ICML 2024] Official code for the paper "Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ".☆83Updated 7 months ago
- ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training☆201Updated 2 years ago
- [ICLR'23] Trainability Preserving Neural Pruning (PyTorch)☆32Updated last year
- code for NASViT☆68Updated 2 years ago
- ☆35Updated 3 years ago