nninit

Weight initializers

Provides weight initialization schemes for PyTorch neural networks

Weight initialization schemes for PyTorch nn.Modules

GitHub

70 stars
4 watching
8 forks
Language: Python
last commit: almost 8 years ago
pytorchweight-initialization-schemes

Related projects:

Repository Description Stars
kaixhin/nninit Provides parameter initialisation schemes for neural network modules in Torch7 100
fgxaos/pytorch-innvestigate PyTorch implementation of an explainability technique for deep neural networks 9
akanimax/pro_gan_pytorch Implementation of a deep learning model for generating high-quality images with improved stability and variation. 538
philkr/magic_init This code provides an initialization method for convolutional neural networks based on data-dependent parameters. 138
chenxi116/pnasnet.pytorch PyTorch implementation of PNASNet-5 architecture 317
ericsun99/shufflenet-v2-pytorch A PyTorch implementation of a ShuffleNet-v2 neural network architecture for image classification. 431
jhjacobsen/pytorch-i-revnet Deep invertible neural network implementation using PyTorch for image recognition and reconstruction tasks. 390
hassony2/kinetics_i3d_pytorch Transfers pre-trained I3D network weights from TensorFlow to PyTorch 532
graal-research/poutyne A PyTorch framework simplifying neural network training with automated boilerplate code and callback utilities 572
harshtrivedi/nmn-pytorch A PyTorch implementation of Neural Module Networks for Visual Question Answering 108
wlwkgus/noisynaturalgradient PyTorch implementation of Noisy Natural Gradient as Variational Inference for Bayesian Neural Networks 121
blue-season/pywarm A lightweight neural network construction API for PyTorch. 184
randl/shufflenetv2-pytorch An implementation of a lightweight convolutional neural network architecture for mobile devices 191
tobiascz/mnist_pytorch_python_and_capi An example project demonstrating how to train and deploy a neural network in Python and C++ using PyTorch 1.0 96
michaelklachko/pnn.pytorch A PyTorch implementation of a neural network architecture that modifies the input to its layers by applying noise masks. 57