bigBatch
Batch trainer
A tool for training neural networks using large batch sizes and analyzing the trade-offs between longer training periods and better generalization performance.
Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training of neural networks"
148 stars
8 watching
24 forks
Language: Python
last commit: over 7 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 openbmb/bmtrain | A toolkit for training large models in a distributed manner while keeping code simple and efficient. | 570 |
 bigscience-workshop/megatron-deepspeed | A collection of tools and scripts for training large transformer language models at scale | 1,342 |
| openbmb/cpm-live | A live training platform for large-scale deep learning models, allowing community participation and collaboration in model development and deployment. | 511 |
 jbloomaus/saelens | A tool for training and analyzing sparse autoencoders to improve the understanding of neural networks and create safer AI systems. | 526 |
 martinkersner/train-deeplab | Trains DeepLab model for semantic image segmentation using annotated data and various training procedures | 172 |
 madrylab/robustness | A library for training and evaluating neural networks with a focus on adversarial robustness. | 921 |
| eladhoffer/convnet.pytorch | A PyTorch implementation of various deep convolutional networks for efficient training and evaluation on diverse datasets. | 347 |
 neuralhydrology/neuralhydrology | A Python library for training neural networks with focus on hydrological applications using PyTorch. | 372 |
 zhanghang1989/pytorch-encoding | A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,044 |
 maxpumperla/elephas | Enables distributed deep learning with Keras and Spark for scalable model training | 1,574 |
 intelligent-machine-learning/dlrover | Automates large-scale deep learning training on distributed clusters, providing fault tolerance and fast recovery from failures. | 1,302 |
 bobazooba/xllm | A tool for training and fine-tuning large language models using advanced techniques | 387 |
 ahmedfgad/neuralgenetic | Trains artificial neural networks using the genetic algorithm | 241 |
 microsoft/megatron-deepspeed | Research tool for training large transformer language models at scale | 1,926 |
 6-billionaires/trading-gym | A platform for training reinforcement learning agents to trade in financial markets. | 230 |