# Efficient Image Classification

A lightweight RDNet image classification model trained on the ImageNet-1k dataset, with 24M parameters and 82.8% top-1 accuracy.

LSNet is a family of lightweight vision models inspired by the dynamic multi-scale capabilities of the human visual system, achieving a balance between performance and efficiency across various vision tasks.

Hiera is a hierarchical vision Transformer model that is fast, powerful, and concise. It surpasses state-of-the-art performance in a wide range of image and video tasks while significantly improving runtime speed.

EfficientNet is a mobile-friendly pure convolutional model that uniformly scales depth/width/resolution dimensions through compound coefficients, trained on the ImageNet-1k dataset.

EfficientNet is a mobile-friendly pure convolutional model that uniformly scales depth/width/resolution dimensions through compound coefficients, trained on the ImageNet-1k dataset.

EfficientNet is a mobile-friendly pure convolutional neural network that achieves efficient scaling by uniformly adjusting depth/width/resolution dimensions through compound coefficients

EfficientNet is a mobile-friendly pure convolutional model that achieves excellent performance in image classification tasks by uniformly scaling depth/width/resolution dimensions with compound coefficients.

EfficientNetV2 is a highly efficient convolutional neural network architecture, specially optimized for training speed and parameter efficiency. The 61-channel version is a variant of this architecture.

LeViT-128S is a vision Transformer model pretrained on the ImageNet-1k dataset, combining the advantages of convolutional networks for faster inference.

LeViT-192 is a vision model that combines convolutional neural networks and Transformer architecture, focusing on image classification tasks.

LeViT-384 is a vision Transformer model pre-trained on the ImageNet-1k dataset, combining the advantages of convolutional networks for faster inference speed.

RegNet image classification model trained on ImageNet-1k, featuring an efficient network structure designed through neural architecture search

ReXNet-1.3x is an image classification model based on the ReXNet architecture, pretrained on the ImageNette dataset. The model reduces channel redundancy by improving the Squeeze-Excitation layers in residual blocks.

DeiT is an efficiently trained vision Transformer model, pretrained and fine-tuned on the ImageNet-1k dataset, suitable for image classification tasks.

ReXNet-1.5x is a lightweight image classification model pretrained on the ImageNette dataset, utilizing the ReXNet architecture. It reduces channel redundancy by improving the Squeeze-Excitation layers within residual blocks.