The application of deep-learning technology for marine fishery resource investigation is still in its infancy stage. In this study, we applied YOLOv5 and YOLOv8 methods to identify and segment fish in the seabed. Our results show that both methods could achieve superior performance in the segmentation task of the DeepFish dataset. We also expanded the labeling of specific fish species classification tags on the basis of the original semantic segmentation dataset of DeepFish and completed the multi-class instance segmentation task of fish based on the newly labeled tags. Based on the above two achievements, we propose a general and flexible self-iterative fish identification and segmentation standard workflow that can effectively improve the efficiency of fish surveys.

Deep learning models provide a novel research perspective for hydraulic machinery and fluid dynamics mechanism research. Traditional computational fluid dynamics requires a lot of computational resource and calculation time, while deep learning models can effectively solve this problem. In this paper, a deep learning model is proposed for the rapid flow field analysis of a two-dimensional cylindrical bypass flow, and the errors of the prediction results are analyzed, so as to verify the feasibility of deep learning for accelerating the numerical simulation process. On this basis, the influence of different network structures on the prediction performance of the deep learning model is explored, and the optimal structural parameters of the neural network are found, indicating that it will achieve real-time prediction of the flow field performance, and save considerable computational resource and calculation time. The research in this paper is of great significance for the application about the rapid analysis of hydraulic machinery fluid dynamics based on deep learning models.