Simple, Scalable. trace-recorder is a trace recorder.

A PyTorch implementation of EfficientNet

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

An implementation of the focal loss to be used with LightGBM for binary and multi-class classification problems

史上最大规模1.4亿中文知识图谱开源下载

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

LSTM-CRF in PyTorch

A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error ＝ 0.34%.