This paper presents a novel approach to automate the detection and classification of different stages of strawberry development using the deep learning model. This research work depicts the classification of different phases of strawberry growth, with a particular focus on the transition from the white to red stages. The single shot strawberry stage detection deep learning model called SSDNet (Strawberry Stages Detect Net) is proposed in this paper to categorize the various developmental phases accurately. The YOLOv8s.pt model is implemented in the Convolutional Neural Network (CNN) classifies the six stages of strawberry such as white, green, early-turning, turning, late-turning and red respectively. The YOLOv8s.pt model is trained with the original RGB images of strawberries, validated and tested with the realtime data. The experimental results revealed the real-time identification of developmental stages of strawberries with high accuracy. The SSDNet model determines an effective and accurate way to monitor and assess the growth stages very swiftly due to its robust performance in detecting elusive variations in strawberry color and morphology. The effectiveness and reliability of the approach across a range of strawberry cultivators and environmental circumstances is proved through testing and validation. The experiment results of YOLOv8s.pt model revealed a precision rate of 94.26%, an accuracy rate of 93.15%, and a recall rate of 90.72% in distinguishing between six different stages of strawberry growth. By combining cutting-edge computer vision technology with agricultural methods, more opportunities for improved fruit production monitoring and optimization are created, which supports sustainable agriculture and food security.