resnet-1k-layers
Neural network architecture
Represents a neural network architecture with 1K layers, designed for image recognition tasks.
Deep Residual Networks with 1K Layers
909 stars
65 watching
249 forks
Language: Lua
last commit: almost 8 years ago
Linked from 2 awesome lists
Related projects:
Repository | Description | Stars |
---|---|---|
| A Torch implementation of a novel neural network architecture designed to improve the generalization ability of deep image classification models. | 129 |
| An implementation of ResNeXt models in Keras, allowing for efficient deep neural networks for image classification. | 224 |
| An implementation of a PyTorch-based neural network architecture for image classification tasks. | 68 |
| An implementation of a 1-bit weight neural network architecture using PyTorch | 124 |
| An MXNet implementation of a modified deep neural network architecture for image classification | 67 |
| A lightweight C library for constructing and training small to medium neural networks with customizable architecture | 689 |
| An implementation of Neural Architecture Search using Reinforcement Learning with a Controller RNN. | 433 |
| An image classification model using the ResNet-50 architecture, trained on the ImageNet dataset. | 14 |
| An implementation of a deep neural network architecture using attention mechanisms and residual connections for image classification tasks. | 554 |
| Provides pre-trained models and training configurations for a deep neural network architecture optimized for image classification tasks | 2,181 |
| Provides a Keras implementation of a deep neural network architecture combining ResNeXt and DenseNet elements | 114 |
| A minimal C library for training and using feedforward artificial neural networks | 2,017 |
| An open-source C++ library for building and training neural networks | 120 |
| Represents an implementation of the Inception-ResNet v2 deep learning model in Keras. | 180 |
| An implementation of a deep neural network architecture for image classification tasks | 273 |