基于Swin-Unet自适应多尺度训练、多类别分割、迁移学习：前列腺分割【包含切片好的数据、代码、训练好的结果等等】

[train hyper-parameters: Namespace(batch_size=8, epochs=100, lr=0.005, lrf=0.001)] [epoch: 1] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 2] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 3] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 4] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 5] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 6] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 7] global correct: 0.9159 precision: ['0.9718', '0.0405', '0.2560'] recall: ['0.9450', '0.0002', '0.5268'] IoU: ['0.9197', '0.0002', '0.2082'] mean IoU: 0.3760 [epoch: 8] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 9] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 10] global correct: 0.9481 precision: ['0.9481', '0.0000', '0.0000'] recall: ['1.0000', '0.0000', '0.0000'] IoU: ['0.9481', '0.0000', '0.0000'] mean IoU: 0.3160 [epoch: 11] global correct: 0.9485 precision: ['0.9485', '0.0000', '0.8807'] recall: ['1.0000', '0.0000', '0.0100'] IoU: ['0.9485', '0.0000', '0.0100'] mean IoU: 0.3195 [epoch: 12] global correct: 0.9640 precision: ['0.9700', '0.0000', '0.7370'] recall: ['0.9967', '0.0000', '0.5022'] IoU: ['0.9669', '0.0000', '0.4258'] mean IoU: 0.4642 [epoch: 13] global correct: 0.9710 precision: ['0.9807', '0.0000', '0.7274'] recall: ['0.9947', '0.0000', '0.7365'] IoU: ['0.9757', '0.0000', '0.5772'] mean IoU: 0.5176 [epoch: 14] global correct: 0.9667 precision: ['0.9914', '0.0000', '0.5781'] recall: ['0.9831', '0.0000', '0.9131'] IoU: ['0.9748', '0.0000', '0.5479'] mean IoU: 0.5076 [epoch: 15] global correct: 0.9562 precision: ['0.9565', '0.0000', '0.9254'] recall: ['0.9998', '0.0000', '0.2181'] IoU: ['0.9563', '0.0000', '0.2144'] mean IoU: 0.3902 [epoch: 16] global correct: 0.9673 precision: ['0.9920', '0.0000', '0.5800'] recall: ['0.9835', '0.0000', '0.9183'] IoU: ['0.9757', '0.0000', '0.5515'] mean IoU: 0.5091 [epoch: 17] global correct: 0.9728 precision: ['0.9882', '0.0000', '0.6741'] recall: ['0.9912', '0.0000', '0.8727'] IoU: ['0.9796', '0.0000', '0.6138'] mean IoU: 0.5311 [epoch: 18] global correct: 0.9751 precision: ['0.9872', '0.0000', '0.7183'] recall: ['0.9944', '0.0000', '0.8518'] IoU: ['0.9818', '0.0000', '0.6386'] mean IoU: 0.5401 [epoch: 19] global correct: 0.9743 precision: ['0.9796', '0.0000', '0.8216'] recall: ['0.9985', '0.0000', '0.7297'] IoU: ['0.9782', '0.0000', '0.6299'] mean IoU: 0.5360 [epoch: 20] global correct: 0.9706 precision: ['0.9935', '0.3750', '0.6050'] recall: ['0.9860', '0.0001', '0.9416'] IoU: ['0.9797', '0.0001', '0.5832'] mean IoU: 0.5210 [epoch: 21] global correct: 0.9762 precision: ['0.9909', '0.2121', '0.6968'] recall: ['0.9930', '0.0001', '0.9156'] IoU: ['0.9840', '0.0001', '0.6547'] mean IoU: 0.5463 [epoch: 22] global correct: 0.9770 precision: ['0.9868', '0.1449', '0.7558'] recall: ['0.9966', '0.0002', '0.8469'] IoU: ['0.9835', '0.0002', '0.6649'] mean IoU: 0.5496 [epoch: 23] global correct: 0.9754 precision: ['0.9812', '0.1385', '0.8174'] recall: ['0.9983', '0.0002', '0.7612'] IoU: ['0.9796', '0.0002', '0.6506'] mean IoU: 0.5435 [epoch: 24] global correct: 0.9757 precision: ['0.9926', '0.2632', '0.6744'] recall: ['0.9915', '0.0012', '0.9406'] IoU: ['0.9841', '0.0012', '0.6468'] mean IoU: 0.5440 [epoch: 25] global correct: 0.9690 precision: ['0.9960', '0.1622', '0.5802'] recall: ['0.9831', '0.0080', '0.9719'] IoU: ['0.9792', '0.0076', '0.5706'] mean IoU: 0.5191 [epoch: 26] global correct: 0.9659 precision: ['0.9970', '0.0939', '0.5470'] recall: ['0.9796', '0.0042', '0.9797'] IoU: ['0.9767', '0.0040', '0.5408'] mean IoU: 0.5072 [epoch: 27] global correct: 0.9783 precision: ['0.9868', '0.3782', '0.7824'] recall: ['0.9974', '0.0021', '0.8601'] IoU: ['0.9843', '0.0021', '0.6941'] mean IoU: 0.5601 [epoch: 28] global correct: 0.9718 precision: ['0.9951', '0.1354', '0.6133'] recall: ['0.9866', '0.0079', '0.9574'] IoU: ['0.9819', '0.0075', '0.5970'] mean IoU: 0.5288 [epoch: 29] global correct: 0.9770 precision: ['0.9921', '0.3204', '0.6983'] recall: ['0.9931', '0.0131', '0.9285'] IoU: ['0.9853', '0.0127', '0.6627'] mean IoU: 0.5536 [epoch: 30] global correct: 0.9787 precision: ['0.9887', '0.4541', '0.7682'] recall: ['0.9967', '0.0205', '0.8836'] IoU: ['0.9854', '0.0200', '0.6976'] mean IoU: 0.5677 [epoch: 31] global correct: 0.9773 precision: ['0.9935', '0.3439', '0.6925'] recall: ['0.9927', '0.0232', '0.9434'] IoU: ['0.9863', '0.0222', '0.6649'] mean IoU: 0.5578 [epoch: 32] global correct: 0.9787 precision: ['0.9899', '0.4352', '0.7575'] recall: ['0.9959', '0.0480', '0.8909'] IoU: ['0.9859', '0.0452', '0.6932'] mean IoU: 0.5748 [epoch: 33] global correct: 0.9785 precision: ['0.9924', '0.3970', '0.7280'] recall: ['0.9941', '0.0532', '0.9291'] IoU: ['0.9866', '0.0492', '0.6897'] mean IoU: 0.5752 [epoch: 34] global correct: 0.9708 precision: ['0.9970', '0.2140', '0.6186'] recall: ['0.9840', '0.0712', '0.9728'] IoU: ['0.9811', '0.0565', '0.6081'] mean IoU: 0.5485 [epoch: 35] global correct: 0.9762 precision: ['0.9950', '0.3066', '0.6818'] recall: ['0.9905', '0.0729', '0.9506'] IoU: ['0.9856', '0.0626', '0.6585'] mean IoU: 0.5689 [epoch: 36] global correct: 0.9781 precision: ['0.9939', '0.3851', '0.7164'] recall: ['0.9928', '0.0947', '0.9348'] IoU: ['0.9868', '0.0823', '0.6823'] mean IoU: 0.5838 [epoch: 37] global correct: 0.9770 precision: ['0.9945', '0.3501', '0.7043'] recall: ['0.9913', '0.1106', '0.9385'] IoU: ['0.9859', '0.0918', '0.6732'] mean IoU: 0.5836 [epoch: 38] global correct: 0.9794 precision: ['0.9900', '0.4302', '0.7717'] recall: ['0.9964', '0.0571', '0.8935'] IoU: ['0.9865', '0.0531', '0.7067'] mean IoU: 0.5821 [epoch: 39] global correct: 0.9798 precision: ['0.9900', '0.4773', '0.7877'] recall: ['0.9964', '0.1054', '0.8877'] IoU: ['0.9864', '0.0945', '0.7164'] mean IoU: 0.5991 [epoch: 40] global correct: 0.9790 precision: ['0.9856', '0.4894', '0.8380'] recall: ['0.9984', '0.0727', '0.8284'] IoU: ['0.9840', '0.0676', '0.7140'] mean IoU: 0.5885 [epoch: 41] global correct: 0.9798 precision: ['0.9889', '0.4910', '0.8047'] recall: ['0.9973', '0.1112', '0.8627'] IoU: ['0.9863', '0.0997', '0.7134'] mean IoU: 0.5998 [epoch: 42] global correct: 0.9797 precision: ['0.9935', '0.4552', '0.7502'] recall: ['0.9943', '0.1505', '0.9211'] IoU: ['0.9878', '0.1275', '0.7049'] mean IoU: 0.6067 [epoch: 43] global correct: 0.9799 precision: ['0.9890', '0.4629', '0.8116'] recall: ['0.9972', '0.1218', '0.8625'] IoU: ['0.9862', '0.1067', '0.7186'] mean IoU: 0.6038 [epoch: 44] global correct: 0.9789 precision: ['0.9849', '0.4799', '0.8450'] recall: ['0.9986', '0.0590', '0.8244'] IoU: ['0.9835', '0.0554', '0.7161'] mean IoU: 0.5850 [epoch: 45] global correct: 0.9797 precision: ['0.9887', '0.4602', '0.8081'] recall: ['0.9972', '0.1059', '0.8644'] IoU: ['0.9860', '0.0942', '0.7172'] mean IoU: 0.5991 [epoch: 46] global correct: 0.9802 precision: ['0.9908', '0.4997', '0.7819'] recall: ['0.9962', '0.1076', '0.9001'] IoU: ['0.9871', '0.0972', '0.7195'] mean IoU: 0.6012 [epoch: 47] global correct: 0.9803 precision: ['0.9895', '0.5044', '0.8081'] recall: ['0.9972', '0.1337', '