Non-official implement of Paper：CBAM: Convolutional Block Attention Module

The codes are PyTorch re-implement version for paper: CBAM: Convolutional Block Attention Module

Woo S, Park J, Lee J Y, et al. CBAM: Convolutional Block Attention Module[J]. 2018. ECCV2018

The overview of CBAM. The module has two sequential sub-modules: channel and spatial. The intermediate feature map is adaptively refined through our module (CBAM) at every convolutional block of deep networks.

• Python3
• PyTorch 0.4.1
• tensorboardX (optional)
• torchnet
• pretrainedmodels (optional)

We just test four models in ImageNet-1K, both train set and val set are scaled to 256(minimal side), only use Mirror and RandomResizeCrop as training data augmentation, during validation, we use center crop to get 224x224 patch.