nninit
Weight initializers
Provides weight initialization schemes for PyTorch neural networks
Weight initialization schemes for PyTorch nn.Modules
70 stars
4 watching
8 forks
Language: Python
last commit: almost 8 years ago pytorchweight-initialization-schemes
Related projects:
Repository | Description | Stars |
---|---|---|
| Provides parameter initialisation schemes for neural network modules in Torch7 | 100 |
| PyTorch implementation of an explainability technique for deep neural networks | 9 |
| Implementation of a deep learning model for generating high-quality images with improved stability and variation. | 538 |
| This code provides an initialization method for convolutional neural networks based on data-dependent parameters. | 138 |
| PyTorch implementation of PNASNet-5 architecture | 317 |
| A PyTorch implementation of a ShuffleNet-v2 neural network architecture for image classification. | 431 |
| Deep invertible neural network implementation using PyTorch for image recognition and reconstruction tasks. | 390 |
| Transfers pre-trained I3D network weights from TensorFlow to PyTorch | 532 |
| A PyTorch framework simplifying neural network training with automated boilerplate code and callback utilities | 572 |
| A PyTorch implementation of Neural Module Networks for Visual Question Answering | 108 |
| PyTorch implementation of Noisy Natural Gradient as Variational Inference for Bayesian Neural Networks | 121 |
| A lightweight neural network construction API for PyTorch. | 184 |
| An implementation of a lightweight convolutional neural network architecture for mobile devices | 191 |
| An example project demonstrating how to train and deploy a neural network in Python and C++ using PyTorch 1.0 | 96 |
| A PyTorch implementation of a neural network architecture that modifies the input to its layers by applying noise masks. | 57 |