1.SE-Net Moudle: SENet enhances the representational capabilities of convolutional neural networks by introducing a new structural unit - the "Squeeze-and-Excitation" (SE) block. It is to improve the representation ability of convolutional neural networks (CNN) by explicitly modeling the dependencies between convolutional feature channels, thereby significantly improving network performance with almost no increase in computational cost. The SE module consists of two main operations: compression (Squeeze) and excitation (Excitation) article: Squeeze-and-Excitation Networks