Skip to content

kobiso/CBAM-keras

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CBAM-Keras

This is a Keras implementation of "CBAM: Convolutional Block Attention Module". This repository includes the implementation of "Squeeze-and-Excitation Networks" as well, so that you can train and compare among base CNN model, base model with CBAM block and base model with SE block.

CBAM: Convolutional Block Attention Module

CBAM proposes an architectural unit called "Convolutional Block Attention Module" (CBAM) block to improve representation power by using attention mechanism: focusing on important features and supressing unnecessary ones. This research can be considered as a descendant and an improvement of "Squeeze-and-Excitation Networks".

Diagram of a CBAM_block

Diagram of each attention sub-module

Classification results on ImageNet-1K

Prerequisites

  • Python 3.x
  • Keras

Prepare Data set

This repository use Cifar10 dataset. When you run the training script, the dataset will be automatically downloaded. (Note that you can not run Inception series model with Cifar10 dataset, since the smallest input size available in Inception series model is 139 when Cifar10 is 32. So, try to use Inception series model with other dataset.)

CBAM_block and SE_block Supportive Models

You can train and test base CNN model, base model with CBAM block and base model with SE block. You can run CBAM_block or SE_block added models in the below list.

  • Inception V3 + CBAM / + SE
  • Inception-ResNet-v2 + CBAM / + SE
  • ResNet_v1 + CBAM / + SE (ResNet20, ResNet32, ResNet44, ResNet56, ResNet110, ResNet164, ResNet1001)
  • ResNet_v2 + CBAM / + SE (ResNet20, ResNet56, ResNet110, ResNet164, ResNet1001)
  • ResNeXt + CBAM / + SE
  • MobileNet + CBAM / + SE
  • DenseNet + CBAM / + SE (DenseNet121, DenseNet161, DenseNet169, DenseNet201, DenseNet264)

Change Reduction ratio

To change reduction ratio, you can set ratio on se_block and cbam_block method in models/attention_module.py

Train a Model

You can simply train a model with main.py.

  1. Set a model you want to train.
    • e.g. model = resnet_v1.resnet_v1(input_shape=input_shape, depth=depth, attention_module=attention_module)
  2. Set attention_module parameter
    • e.g. attention_module = 'cbam_block'
  3. Set other parameter such as batch_size, epochs, data_augmentation and so on.
  4. Run the main.py file
    • e.g. python main.py

Related Works

Reference

Author

Byung Soo Ko / kobiso62@gmail.com

About

CBAM implementation on Keras

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages