The field of assisted reproductive technology (ART) has significantly advanced with the integration of machine learning techniques. This research work developed a deep learning based system that automates the classification of embryo development stages using convolutional neural networks (CNNs) based on the Inception architecture. The system processes time-lapsed embryo images efficiently by managing, organizing and preprocessing the collection from datasets. Leveraging CNNs to analyze and classify the developmental stages with high accuracy aids infertility specialists in selecting the most viable embryos for implantation. This automation not only enhances the precision of embryo selection but also improves the overall success rates and patient outcomes in infertility treatments.