princeton-vl / CornerNet-Lite

BSD 3-Clause "New" or "Revised" License
1.78k stars 431 forks source link

Problem when evaluate my own datasets #121

Closed qingzhoudong closed 4 years ago

qingzhoudong commented 4 years ago

after i trained my own datasets, i want to evaluate AP, but there are some problems that i can't solve. File "evaluate.py", line 106, in <module> main(args) File "evaluate.py", line 102, in main test(testing_db, system_config, model, args) File "evaluate.py", line 62, in test test_func(system_config, db, nnet, result_dir, debug=debug) File "/home/qzdong/CornerNet-Lite-master/core/test/__init__.py", line 5, in test_func return globals()[sys_config.sampling_function](db, nnet, result_dir, debug=debug) File "/home/qzdong/CornerNet-Lite-master/core/test/cornernet_saccade.py", line 282, in cornernet_saccade detections = db.convert_to_coco(top_bboxes) File "/home/qzdong/CornerNet-Lite-master/core/dbs/coco.py", line 143, in convert_to_coco category_id = self._cls2coco[cls_ind] KeyError: 6 what should i do to solve this problem?