
ConvNeXt
A pure ConvNet model constructed entirely from standard ConvNet modules, designed for the 2020s.
Discover the strongest tools and workflows for classify images.

A pure ConvNet model constructed entirely from standard ConvNet modules, designed for the 2020s.

Vision Transformer and MLP-Mixer architectures for image recognition and processing.

Hierarchical Vision Transformer using Shifted Windows for general-purpose computer vision tasks.

A large-sized Vision Transformer model pre-trained on ImageNet for image classification tasks.

Automated Multimodal Image Recognition and SEO-Optimized Alt-Text Generation

A transformer adapted for computer vision tasks by treating images as sequences of patches.

The performance-first computer vision augmentation library for high-accuracy deep learning pipelines.

The high-performance deep learning framework for flexible and efficient distributed training.

State-of-the-art AutoML for tabular, image, text, and time-series data using multi-layer stacking.