AI Agent Skills

PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation…

🖼️🎨 A PyTorch reimplementation of the paper Free-Form Image Inpainting with Gated Convolution (DeepFill v2) (https://arxiv.org/abs/1806.03589)

ConvMAE: Masked Convolution Meets Masked Autoencoders