Deep learning topic
Deep learning is an AI function and a subset of machine learning, used for processing large amounts of complex data. Deep learning can automatically create algorithms based on data patterns.
PlanGen
[EMNLP'21] Plan-then-Generate: Controlled Data-to-Text Generation via Planning
nexus
Experimental tensor-typed deep learning
Contrastive-Learning-with-Non-Semantic-Negatives
Robust Contrastive Learning Using Negative Samples with Diminished Semantics (NeurIPS 2021)
img_classification_pk_pytorch
Quickly comparing your image classification models with the state-of-the-art models (such as DenseNet, ResNet, ...)
learning-at-home
"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts" (NeurIPS 2020), original PyTorch implementation
MSDNet
Multi-Scale Dense Networks for Resource Efficient Image Classification （ICLR 2018 Oral）
SnapshotEnsemble
Snapshot Ensembles in Torch (Snapshot Ensembles: Train 1, Get M for Free)
Anime-InPainting
An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复，去马赛克，填补，去瑕疵
ACER
Actor-critic with experience replay