Is this lc0? Definitely not. Lc0 is a clone of alpha zero chess, based on the paper by Deep Mind. Also, lc0 is a somewhat complicated, brittle bit of C++ code that runs into the thousand of lines. A0lite, by contrast, is a very si
TorchFlare is a simple, beginner-friendly and an easy-to-use PyTorch Framework train your models without much effort. It provides an almost Keras-like experience for training your models with all the callbacks, metrics, etc
The Vision Transformer (ViT) heavily depends on pretraining using ultra large-scale datasets (e.g. ImageNet-21K or JFT-300M) to achieve high performance, while significantly underperforming on ImageNet-1K if trained from scratch.
This is the official PyTorch implementation of TMNet in the CVPR 2021 paper "Temporal Modulation Network for Controllable Space-Time Video Super-Resolution". Our TMNet can flexibly interpolate intermediate frames for space-time vi
DeepMetaHandles is a shape deformation technique. It learns a set of meta-handles for each given shape. The disentangled meta-handles factorize all the plausible deformations of the shape, while each of them corresponds to an intu
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks
This project provides the implementation for the CVPR 2021 paper "Scale-aware Automatic Augmentation for Object Detection". Scale-aware AutoAug provides a new search space and search metric to find effective data agumentation poli