<p>This study presents an innovative approach to implement the Full waveform inversion of cross-hole Ground Penetrating Radar (GPR) data using a Markov Chain Monte Carlo (MCMC) method that incorporates a SE-Residual Network (ResNet). The cross - hole GPR technique is widely used in geophysical prospecting for its ability to obtain high - resolution subsurface information. However, traditional full waveform inversion methods for GPR data often face challenges such as high computational cost and being trapped in local minima. The SE (Squeeze-and-Excitation) attention mechanism can enhance the capability of ResNet. By integrating the SE - ResNet into the MCMC method, this proposed approach aims to overcome these limitations. The SE - ResNet, with its ability to capture complex feature representations and perform effective channel - wise feature recalibration, can help in better understanding the characteristics of GPR data. This understanding is then utilized by the MCMC method to sample more efficiently from the posterior distribution of the model parameters. Numerical experiments demonstrate that compared to ResNet, SE-ResNet networks have smaller root mean square error (RMSE) and can effectively perform Full waveform inversion. The findings of this study highlight the effectiveness of combining SE attention mechanisms with ResNet architectures for complex data inversion tasks.</p>