dni-pytorch
by koz4k
Decoupled Neural Interfaces using Synthetic Gradients for PyTorch
AI summary
Message passing abstraction
Decoupled Neural Interfaces using Synthetic Gradients for PyTorch
- stars
- 236
- forks
- 38
- watching
- 10
Similar projects
Found by comparing what the projects do, not just their names.
Decoupled Neural Interface
An implementation of synthetic gradients to decouple neural network layers and enable scalable communication between them
Computer Vision Toolkit
A PyTorch toolbox for supporting research and development of domain adaptation, generalization, and semi-supervised learning methods in computer vision.
Deep learning models
Implementations of deep learning architectures using PyTorch for image classification tasks on various datasets.
Deep learning toolkit
A Python framework for building deep learning models with optimized encoding layers and batch normalization.
EfficientNet model
A PyTorch implementation of EfficientNet for computer vision tasks
Adversarial attacks library
PyTorch implementation of various Convolutional Neural Network adversarial attack techniques
PyTorch tutorial
An introduction to using PyTorch for deep learning tasks
Pruning tool
This project provides a PyTorch implementation of pruning techniques to reduce the computational resources required for neural network inference.
DNCs
An implementation of Differentiable Neural Computers and family for PyTorch, enabling scalable memory-augmented neural networks.
Image evaluator
Assesses and evaluates images using deep learning models
ResNet simulator
Reproduces ResNet-V3 with PyTorch for computer vision tasks
Memory optimizer for deep learning models
A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution
Image Segmentation Model
PyTorch implementation of a deep learning model for image segmentation
Neural Network Training Demo
An example project demonstrating how to train and deploy a neural network in Python and C++ using PyTorch 1.0
Neural net trainer
A PyTorch framework simplifying neural network training with automated boilerplate code and callback utilities
