深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

Multi-scale discriminator feature-wise loss function

source code of “Visual Saliency Transformer” (ICCV2021)

Deep learning training framework for image super resolution and restoration.

ECCV2022: Improving the Perceptual Quality of 2D Animation Interpolation

Dataset of native FHD (1080p) anime productions

PyTorch code and models for the DINOv2 self-supervised learning method.

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

Align Anything: Training All-modality Model with Feedback