关于一些经典论文源码Source Code的中文笔记，尽量做到整体框架梳理和逐行源码注释。
-
不过太早期的代码一般都模块化了，所以主要更一些后期(2017-NOW)的笔记。
-
语言主要是Pytorch和Tensorflow版本的代码，部分Keras。
-
部分代码Run起来需要涉及到配置、数据集和预训练模型，请对应原文章的源码进行操作。
-
有注解错误和思路问题欢迎讨论。
欢迎访问博客：https://nakaizura.blog.csdn.net/
推荐系统
| Recommendation | Notebook | keywords |
|---|---|---|
| BPR | Notebook | Pair-wise |
| NFM | Notebook | MLP+FM |
| AFM | Notebook | Attention+FM |
| NCF | Notebook | MLP+MF |
| ONCF | Notebook | Out-product+NCF |
| DIN | Notebook | Attention+Interest |
| DRL-REC | Notebook | RL in Rec |
| IRGAN | Notebook | GAN in Rec |
| RippleNet | Notebook | KG in Rec |
| NGCF | Notebook | Graph in Rec |
| LightGCN | Notebook | Light Vesion NGCF |
| SR-GNN | Notebook | Session-based GNN |
图神经网络
| Graph | Notebook | keywords |
|---|---|---|
| Louvain | Notebook | Community Detection |
| DeepWalk | Notebook | Graph Embedding |
| node2vec | Notebook | Graph Embedding Plus |
| GCN | Notebook | Spectral Convolutional |
| GAT | Notebook | Spatial+Attention |
| GraphSAGE | Notebook | Inductive |
| GAE | Notebook | Graph Autoencoder |
| HetGNN | Notebook | Heterogeneous |
| Scenegraph | Notebook | Relationship Triplet |
| Graph Transformer | Notebook | Graph Transformer |
计算机视觉
| CV | Notebook | keywords |
|---|---|---|
| DCGAN | Notebook | GAN in CV |
| InfoGAN | Notebook | Info Control |
| Capsules | Notebook | CNN is Rubbish |
| C3D | Notebook | 3D VGG |
| SlowFast | Notebook | Slow+Fast |
| Non-local | Notebook | Pixel+Attention |
| MoCo | Notebook | Contrastive Learning |
| MIL-NCE | Notebook | Contrastive Learning |
| CLIP | Notebook | CLIP |
| ViT | Notebook | Vsion Transformer |
| MLP-Mixer | Notebook | MLP is All |
自然语言处理
| NLP | Notebook | keywords |
|---|---|---|
| NTM | Notebook | NVDM-GSM |
| Skip-Thought | Notebook | Sentence2vec |
| Transformer | Notebook | Attention is All |
| BERT | Notebook | Pretraning NLP |
| extractive_summarization | Notebook | Extractive Summarization |
| UIE | Notebook | Information Extraction |
| OpenPrompt | Notebook | OpenPrompt |
跨模态
| Cross-modal | Notebook | keywords |
|---|---|---|
| TALL | Notebook | Cross-modal Video Moment Retrieval |
| ACMR | Notebook | Adversarial Cross-modal Retrieval |
| S2VT | Notebook | Cross-modal Video Captioning |
| VMT | Notebook | Cross-modal Video Translation |
| MIL-NCE | Notebook | Cross-modal Align |
| CLIP | Notebook | Cross-modal Pre-training |
| Preparing | Notebook | 待更...... |