不改变原意使其更有逻辑改写：The preprocessed data is randomly divided into the training set validation set and test set with a ratio of 622 And the deep learning framework was PyTorch The optimizer was Adam and the

The preprocessed data was partitioned randomly into three sets: the training set, validation set, and test set, with a ratio of 6:2:2. The deep learning framework used was PyTorch, with the optimizer set to Adam and weight decay set to 0.0001. All models were trained on 8 GPUs with a batch size of 16. The default number of iterations was 100 epochs, and the initial learning rate was set to 0.0001, with a total of 500 epochs. The input size of the image was 512×512.