Mixed-Senet-Densenet

In this repository, I released senet-densenet training codes and output files. And it refer to another repository, which repository I had made some notes in. Chinese version blog, English version blog

Experiments

In another repository, I had made some annotations about different structures of senet-densent, pls check here for more details, and there are some charts and datas visualized by matplotlib too.

Usages:

Download dataset

Cifar10 dataset is easy to access it's website and download it into data/cifar10, you can refer to pytorch official tutorials about how to train on cifar10 dataset.

Training

There are some modules in core folder, before you start training, you need to edit code in cifar10.py file to change from core.se_densenet_xxxx import se_densenet121,

Then, open your terminal, type:

python cifar10.py

Visualize training

In your terminal, type:

python visual/viz.py

Note: please change your state file path in /visual/viz.py.

Refer:

another repo of senet-densenet

Chinese version blog

English version blog