Diabetic Retinopathy (DR) has recently become a major concern for people with diabetes, it is an eye condition that occurred due to severely damaged blood vessels in the retina, leading to visual impairment. According to the projections from the World Health Organization, DR would affect 235 million people by 2040. This research paper presents a convolutional neural network (CNN) model using DenseNet121 architecture, making it more efficient to train for the task of image classification and detecting Diabetic Retinopathy using color fundus images. In this regard, we proposed a model to automate the detection of anomalies in retinal images using cost-effective image processing techniques and also to address the challenges of real-world data. The dataset used for this paper is EYEPACS, consisting of 35,128 color fundus images, which are widely used for training and testing models for detecting Diabetic Retinopathy. The metrics that are used for measuring the performance of our model are accuracy, precision, and F1-Score.