Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
---|---|---|---|---|---|---|---|---|---|---|
Vit Pytorch | 16,298 | 6 | 4 months ago | 184 | November 15, 2023 | 114 | mit | Python | ||
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch | ||||||||||
Text_classification | 7,628 | 7 months ago | 45 | mit | Python | |||||
all kinds of text classification models and more with deep learning | ||||||||||
Transformer | 3,882 | a year ago | 134 | apache-2.0 | Python | |||||
A TensorFlow Implementation of the Transformer: Attention Is All You Need | ||||||||||
X Transformers | 3,840 | 10 | 3 months ago | 317 | December 02, 2023 | 55 | mit | Python | ||
A simple but complete full-attention transformer with a set of promising experimental features from various papers | ||||||||||
A Pytorch Tutorial To Image Captioning | 2,084 | 2 years ago | 97 | mit | Python | |||||
Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning | ||||||||||
Gat | 2,078 | 3 years ago | 27 | mit | Python | |||||
Graph Attention Networks (https://arxiv.org/abs/1710.10903) | ||||||||||
Reformer Pytorch | 1,917 | 10 months ago | 139 | November 06, 2021 | 14 | mit | Python | |||
Reformer, the efficient Transformer, in Pytorch | ||||||||||
Pytorch Gat | 1,815 | a year ago | 12 | mit | Jupyter Notebook | |||||
My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples! | ||||||||||
Pygat | 1,684 | 3 years ago | 32 | mit | Python | |||||
Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903) | ||||||||||
Hopfield Layers | 1,258 | 2 years ago | other | Python | ||||||
Hopfield Networks is All You Need |