Pyramid Attention Networks pytorch
Implementation of Pyramid Attention Networks for Semantic Segmentation.
A Pytorch implementation of [Pyramid Attention Networks for Semantic Segmentation](https://arxiv.org/abs/1805.10180) from 2018 paper by Hanchao Li, Pengfei Xiong, Jie An, Lingxue Wang. The project is written primarily in Python, distributed under the GNU General Public License v3.0 license, first published in 2018. Key topics include: attention, pyramid, semanticsegmentation.
PAN-pytorch
A Pytorch implementation of Pyramid Attention Networks for Semantic Segmentation from 2018 paper by Hanchao Li, Pengfei Xiong, Jie An, Lingxue Wang.
Installation
- Env: Python3.6, Pytorch1.0-preview
- Clone this repository.
- Download the dataset by following the instructions below.
VOC2012 Dataset
The overall dataset is augmented by Semantic Boundaries Dataset, resulting in training data 10582 and test data 1449. https://www.sun11.me/blog/2018/how-to-use-10582-trainaug-images-on-DeeplabV3-code/
After preparing the data, please change the directory below for training.
pythontraining_data = Voc2012('/home/tom/DISK/DISK2/jian/PASCAL/VOC2012', 'train_aug', transform=train_transforms) test_data = Voc2012('/home/tom/DISK/DISK2/jian/PASCAL/VOC2012', 'val',transform=test_transforms)
Evaluation
| Pixel acc | mIOU |
|---|---|
| 93.19% | 78.498% |
Contributors
Showing top 1 contributor by commit count.
Related Repositories
labmlai/annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
ddbourgin/numpy-ml
Machine learning, in numpy
graykode/nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
kyegomez/OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
xmu-xiaoma666/External-Attention-pytorch
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐