The escalating demand for pork highlights the importance of swift and accurate pregnancy diagnosis in sows, a crucial factor in farm profitability. The prevalent use of low-frequency ultrasound devices in this context poses a challenge owing to the suboptimal resolution of the resultant images. This study introduces an innovative approach for sow pregnancy diagnosis using deep learning techniques to analyze low-frequency ultrasound images. Our methodology encompasses the development and comparative analysis of three distinct classification models: ViT-H, ConvNeXt-xlarge, and Xception. These models aim to improve diagnostic accuracy. AutoAugment was used to augment the data to expand the training dataset, thereby enhancing the robustness of the models under varied conditions. Results indicate a notable improvement in diagnostic performance, with the implementation of AutoAugment leading to significant achievements in the models, reflected by AUC values of 0.865, 0.856, and 0.866. These outcomes affirm the viability of deep learning in the effective management of sow pregnancies in livestock farms and suggest potential applications in broader animal husbandry contexts. This research marks a significant contribution to the evolution of agricultural technologies, presenting a scalable and efficacious solution for sow pregnancy diagnosis.