An automated system for detecting ocular diseases with computer-aided tools is essential to identify different eye disorders through fundus pictures. This is because diagnosing ocular illnesses manually is a complicated, time-consuming, and error-prone process. In this research, two multi-label embedded architectures based on a deep learning strategy were proposed for ocular disease recognition and classification. The ODIR (Ocular Disease Intelligent Recognition) dataset was adopted for those models. The suggested designs were implemented as parallel systems. The first model was developed as a parallel embedded system that leverages transfer learning to implement its classifiers. The implementation of these classifiers utilized the deep learning network from VGG16, while the second model was introduced with a parallel architecture, and its classifiers were implemented based on newly proposed deep learning networks. These networks were notable for their small size, limited layers, speedy response, and accurate performance. Therefore, the new proposed design has several benefits, like a small classification network size (20 % of VGG16), enhanced speed, and reduced energy consumption, as well as the suitability for IoT applications that support smart systems like Raspberry Pi and Self-powered components, which possess the ability to function as long as a charged battery is available. The highest accuracy of 0.9974 and 0.96 has been obtained in both proposed models for Myopia ocular disease detection and classification. Compared to research that had been presented in the same field, the performance accuracy of each of the two models shown was high. The P3448-0000 Jetson Nano Developer Kit is used to implement both of the proposed embedded models