Pytorch-NCE
Softmax optimizer
An implementation of Noise Contrastive Estimation in PyTorch to improve the performance and efficiency of softmax output layers
The Noise Contrastive Estimation for softmax output written in Pytorch
317 stars
7 watching
45 forks
Language: Python
last commit: about 5 years ago importance-samplinglanguage-modelncence-criterionpytorchsoftmaxspeedup
Related projects:
| Repository | Description | Stars |
|---|---|---|
 demelin/noise-contrastive-estimation-nce-for-pytorch | An implementation of a Noise Contrastive Estimation algorithm in PyTorch | 45 |
 moskomule/eve.pytorch | An implementation of an optimization algorithm inspired by a 2016 research paper | 33 |
 atgambardella/pytorch-es | An implementation of an optimization algorithm for training neural networks in machine learning environments. | 351 |
 huggingface/optimum-quanto | A PyTorch quantization backend for models. | 847 |
 jiangoforit/yellowfin_pytorch | An optimizer that automatically tunes momentum and learning rate using local quadratic approximation. | 287 |
 bloodaxe/pytorch-toolbelt | A comprehensive Python library with PyTorch extensions for rapid prototyping and machine learning model development. | 1,523 |
 wxywhu/srdensenet-pytorch | A PyTorch implementation of an image super-resolution model based on dense skip connections. | 119 |
 wlwkgus/noisynaturalgradient | PyTorch implementation of Noisy Natural Gradient as Variational Inference for Bayesian Neural Networks | 121 |
 locuslab/optnet | A PyTorch module that adds differentiable optimization as a layer to neural networks | 517 |
 nnaisense/evotorch | An evolutionary computation library built on top of PyTorch for solving optimization problems in various fields. | 1,026 |
 akanimax/pro_gan_pytorch | Implementation of a deep learning model for generating high-quality images with improved stability and variation. | 538 |
 zhanghang1989/pytorch-encoding | A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,044 |
 khanrc/pt.darts | An implementation of DARTS, a method for automatically designing neural network architectures. | 443 |
 metaopt/torchopt | An efficient library for differentiable optimization built on top of PyTorch. | 554 |
 hjmshi/pytorch-lbfgs | A PyTorch implementation of L-BFGS optimization algorithm for training neural networks | 591 |