Discover the best AI tools to help you extract visual features.
High-resolution networks for semantic segmentation tasks.
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.
Sub-millisecond computer vision feature extraction for edge-native AI applications.
The industry-standard drop-in replacement for MNIST for benchmarking fashion-centric deep learning models.
The industry-standard open-source implementation of Contrastive Language-Image Pre-training (CLIP).
The industry-standard deep learning dataset and model suite for state-of-the-art scene recognition.