Corn is one of the important crops in the agricultural sector in the global and national economy because it is a food resource as food, animal feed and other raw materials for the community. Based on satudata.pertanian.go.id, the projected corn production in 2020-2024 will still increase between 0.94% and 0.97% per year. In this study, detection of diseases and pests in maize was carried out using YOLO technology with spatial pyramid pooling (SPP) architecture as a form of intelligent innovation in maize farming. The research data consisted of 309 image data with class values as labels representing types of disease and types of pests in corn plants consisting of Locusta (Locust), Sitophilus (Powder Flower), Spodoptera (Arrayworm), Mysus Persicase (Aphids), and Bulai . The indicators for testing and evaluating the model use precision, recall, f1 score, mAP0.5 and Map0.5:0.95 as evaluation metrics. Based on the results of training and evaluation of the model, it is known that the precision value with batch size 32 epoch 64 produces a precision value of 0.65, recall, 0.76, f1 score 0.65 Map0.5 0.704 and Map-.5:0.95 0.298. Whereas with a batch size of 64 epoch 100 the precision value is 0.73, the recall is 0.77 f1 score is 0.73 Map0.5 0.795 and Map0.5:0.95 0.346. Model predictions using YOLO technology with spatial pyramid pooling architecture in detecting types of diseases and pests in corn plants contribute to smart agriculture. With accurate information about the types of diseases and pests that attack corn plants, farmers can respond quickly and take appropriate actions, such as using specific pesticides or suitable organic control methods.