On the Role of Bidirectionality in Language Model Pre-Training

探讨语言模型预训练中的双向性.

使用pydensecrf构造条件随机场

Building fully-connected conditional random field with pydensecrf.

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

YOLOv7：实时目标检测器的可训练技巧.

Comprehensive Guide to Ultralytics YOLOv5

YOLOv5：YOLO目标检测模型的第五次迭代.

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

ViTPose：用于人体姿态估计的简单视觉Transformer基线.

PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions

PolyLoss：一种分类损失函数的多项式展开视角.