In this paper, we pioneer a new machine-learning method to search for HII regions in spectra from The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST). HII regions are emission nebulae created when young and massive stars ionize nearby gas clouds with high-energy ultraviolet radiation. Having more HII region samples will help us understand the formation and evolution of stars. Machine-learning methods are often applied to search for special celestial bodies such as H II regions. LAMOST has conducted spectral surveys and provided a wealth of valuable spectra for the research of special and rare celestial bodies. To overcome the problem of sparse positive samples and diversification of negative samples, a novel method called the self-calibrated convolution network is introduced and implemented for spectral processing. A deep network classifier with a structure called a self-calibrated block provides a high precision rate, and the recall rate is improved by adding the strategy of positive-unlabeled bagging. Experimental results show that this method can achieve better performance than other current methods. Eighty-nine spectra are identified as Galactic HII regions after cross-matching with the WISE Catalog of Galactic HII Regions, confirming the effectiveness of the method proposed in this paper.