| allenai/bi-att-flow |
1,510 |
|
0 |
0 |
almost 3 years ago |
0 |
|
73 |
apache-2.0 |
Python |
| Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization. |
| openai/sparse_attention |
1,002 |
|
0 |
0 |
over 5 years ago |
0 |
|
10 |
|
Python |
| Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers" |
| datalogue/keras-attention |
656 |
|
0 |
0 |
almost 7 years ago |
0 |
|
22 |
agpl-3.0 |
Python |
| Visualizing RNNs using the attention mechanism |
| sjsdfg/dl4j-tutorials |
429 |
|
0 |
0 |
almost 5 years ago |
0 |
|
0 |
mit |
Java |
| dl4j 基础教程 配套视频：https://space.bilibili.com/327018681/#/ |
| thushv89/attention_keras |
429 |
|
0 |
0 |
about 3 years ago |
0 |
|
11 |
mit |
Python |
| Keras Layer implementation of Attention for Sequential models |
| bytedance/neurst |
232 |
|
0 |
0 |
almost 4 years ago |
3 |
April 14, 2022 |
9 |
other |
Python |
| Neural end-to-end Speech Translation Toolkit |
| harvardnlp/struct-attn |
221 |
|
0 |
0 |
about 9 years ago |
0 |
|
1 |
mit |
Lua |
| Code for Structured Attention Networks https://arxiv.org/abs/1702.00887 |
| MILVLG/mcan-vqa |
181 |
|
0 |
0 |
almost 6 years ago |
0 |
|
2 |
apache-2.0 |
Python |
| Deep Modular Co-Attention Networks for Visual Question Answering |
| tlatkowski/multihead-siamese-nets |
173 |
|
0 |
0 |
over 3 years ago |
0 |
|
12 |
mit |
Jupyter Notebook |
| Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task. |
| zzd1992/Image-Local-Attention |
93 |
|
0 |
0 |
over 4 years ago |
0 |
|
2 |
|
Python |
| A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude. |
