 AdaBound
 AdaBound 
 Optimizer
 An optimizer that combines the benefits of Adam and SGD algorithms
An optimizer that trains as fast as Adam and as good as SGD.
3k stars
 71 watching
 330 forks
 
Language: Python 
last commit: over 2 years ago  Related projects:
| Repository | Description | Stars | 
|---|---|---|
|  | An automated machine learning framework that learns to ensemble sub-networks to improve model quality | 3,470 | 
|  | A toolkit for fine-tuning and inferring large machine learning models | 8,312 | 
|  | An implementation of a deep reinforcement learning algorithm for human-level control in game environments using TensorFlow. | 2,491 | 
|  | A high-performance gradient boosting framework for machine learning tasks | 16,769 | 
|  | A toolkit for optimizing and accelerating the training and inference of machine learning models on various hardware platforms. | 2,618 | 
|  | A framework for building and training AI models on multiple GPUs or TPUs with minimal code changes. | 28,636 | 
|  | A Python library providing tensors and dynamic neural networks with strong GPU acceleration | 84,978 | 
|  | A toolkit for optimizing and deploying artificial intelligence models in various applications | 7,439 | 
|  | An open-source implementation of several reinforcement learning algorithms in PyTorch | 3,644 | 
|  | A high-performance Python profiler that analyzes CPU, GPU, and memory usage, providing detailed information and AI-powered optimization suggestions. | 12,274 | 
|  | A PyTorch implementation of differentiable ODE solvers with GPU support and efficient backpropagation | 5,655 | 
|  | An official PyTorch implementation of the StyleGAN2-ADA algorithm for generating images with a focus on stability and performance. | 4,144 | 
|  | Automates machine learning tasks to train accurate models in just a few lines of code | 8,167 | 
|  | A PyTorch-based library for Bayesian optimization, providing a modular interface for composing and optimizing probabilistic models. | 3,126 | 
|  | Implementations of various deep learning algorithms and techniques with accompanying documentation | 57,177 |