Diabetes is a common disease affects one person out of every 11 people. In 2021, 537 million people in the world were suffering from diabetes, and this number is expected to double in the coming years. Diabetes greatly affects the eyes, such as diabetic retinopathy.It is an eye disease that can affect diabetic patients. When this happens, the blood vessels in the retina are damaged due to high blood sugar levels, which can lead to blindness. So early detection can reduce the risk of blindness. Previously, diagnosing diabetic retinopathy was very difficult and time consuming for ophthalmologists. And now, deep learning has made it easier for ophthalmologists to detect and stages diabetic retinopathy.So early detection can reduce the risk of blindness. Previously, diagnosing diabetic retinopathy was very difficult and time consuming for ophthalmologists. And now, deep learning has made it easier for ophthalmologists to detect and stages diabetic retinopathy.In this project, we focus on using deep neural network and an EfficientNetB3 model to detect and classify diabetic retinopathy stages.