nanodet icon indicating copy to clipboard operation
nanodet copied to clipboard

关于训练到最后一个epoch时,会报错IndexError: list index out of range

Open LaoGanGit opened this issue 3 years ago • 4 comments

Traceback (most recent call last): File "tools/train.py", line 92, in main(args) File "tools/train.py", line 87, in main trainer.run(train_dataloader, val_dataloader, evaluator) File "d:\it\project\pytorch\deep-learning-for-image-processing-master\pytorch_object_detection\nanodet\nanodet\trainer\trainer.py", line 148, in run eval_results = evaluator.evaluate(results, self.cfg.save_dir, epoch, self.logger, rank=self.rank) File "d:\it\project\pytorch\deep-learning-for-image-processing-master\pytorch_object_detection\nanodet\nanodet\evaluator\coco_detect ion.py", line 52, in evaluate results_json = self.results2json(results) File "d:\it\project\pytorch\deep-learning-for-image-processing-master\pytorch_object_detection\nanodet\nanodet\evaluator\coco_detect ion.py", line 40, in results2json category_id = self.cat_ids[label] IndexError: list index out of range 作者您好,这是报错的代码,请教作者出现超出范围是数据集或者config参数哪里没写对吗

LaoGanGit avatar Nov 26 '21 02:11 LaoGanGit

一般来说是num_classes与数据集里的类别数不一致

RangiLyu avatar Nov 26 '21 02:11 RangiLyu

一般来说是num_classes与数据集里的类别数不一致

谢谢作者的解答,这个问题已经解决了

LaoGanGit avatar Nov 26 '21 02:11 LaoGanGit

数据

请问是为什么呢

MagicCodess avatar Mar 11 '22 02:03 MagicCodess

请问是怎么解决的呢

sinx-cosxO-O avatar Mar 24 '23 08:03 sinx-cosxO-O