RotationDetection train多个网络后，test出现问题

Traceback (most recent call last): File "", line 1, in File "D:\PyCharm 2020.1\plugins\python\helpers\pydev_pydev_bundle\pydev_umd.py", line 197, in runfile pydev_imports.execfile(filename, global_vars, local_vars) # execute the script File "D:\PyCharm 2020.1\plugins\python\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "I:/projects/RotationDetection-new/tools/gwd/test_dota.py", line 33, in tester.eval() File "I:/projects/RotationDetection-new/tools/gwd/test_dota.py", line 25, in eval self.test_dota(det_net=gwd, real_test_img_list=real_test_img_list, txt_name=txt_name) File "I:\projects\RotationDetection-new\tools\test_dota_base.py", line 310, in test_dota proc = self.test(int(gpu_id), split_records, det_net, result_queue) File "I:\projects\RotationDetection-new\tools\test_dota_base.py", line 281, in test float(threshold[self.label_name_map[sub_class]]), 0) KeyError: 9 train一个网络后，能成功test，接着训练其他网络，能成功训练，但是不能测试，同时前面的网络也不能测试了