nninit
Weight initialization schemes for PyTorch nn.Modules
AI summary
Weight initializers
Provides weight initialization schemes for PyTorch neural networks
- stars
- 70
- forks
- 8
- watching
- 4
Similar projects
Found by comparing what the projects do, not just their names.
NN init
Provides parameter initialisation schemes for neural network modules in Torch7
Neural network explainer
PyTorch implementation of an explainability technique for deep neural networks
Image generator
Implementation of a deep learning model for generating high-quality images with improved stability and variation.
Data initialization method
This code provides an initialization method for convolutional neural networks based on data-dependent parameters.
PNASNet model
PyTorch implementation of PNASNet-5 architecture
Neural net architecture
A PyTorch implementation of a ShuffleNet-v2 neural network architecture for image classification.
Invertible networks
Deep invertible neural network implementation using PyTorch for image recognition and reconstruction tasks.
I3D weight transfer
Transfers pre-trained I3D network weights from TensorFlow to PyTorch
Neural net trainer
A PyTorch framework simplifying neural network training with automated boilerplate code and callback utilities
NMN
A PyTorch implementation of Neural Module Networks for Visual Question Answering
Bayesian optimizer
PyTorch implementation of Noisy Natural Gradient as Variational Inference for Bayesian Neural Networks
NN builder
A lightweight neural network construction API for PyTorch.
CNN model
An implementation of a lightweight convolutional neural network architecture for mobile devices
Neural Network Training Demo
An example project demonstrating how to train and deploy a neural network in Python and C++ using PyTorch 1.0
Noise mask neural network
A PyTorch implementation of a neural network architecture that modifies the input to its layers by applying noise masks.
