after trained about 7000 iters.it has error.

[henbucuoshanghai]

Traceback (most recent call last): File "projects/SparseRCNN/train_net.py", line 141, in args=(args,), File "/home/SparseR-CNN/detectron2/engine/launch.py", line 62, in launch main_func(*args) File "projects/SparseRCNN/train_net.py", line 129, in main return trainer.train() File "/homeSparseR-CNN/detectron2/engine/defaults.py", line 419, in train super().train(self.start_iter, self.max_iter) File "/home/SparseR-CNN/detectron2/engine/train_loop.py", line 135, in train self.after_step() File "/home/SparseR-CNN/detectron2/engine/train_loop.py", line 165, in after_step h.after_step() File "/home//SparseR-CNN/detectron2/engine/hooks.py", line 356, in after_step self._do_eval() File "/home/SparseR-CNN/detectron2/engine/hooks.py", line 331, in _do_eval results = self._func() File "/home/lSparseR-CNN/detectron2/engine/defaults.py", line 372, in test_and_save_results self._last_eval_results = self.test(self.cfg, self.model) File "/home/inference_on_dataset(model, data_loader, evaluator) File "/home//SparseR-CNN/detectron2/evaluation/evaluator.py", line 176, in inference_on_dataset results = evaluator.evaluate() File "/home//SparseR-CNN/detectron2/evaluation/coco_evaluation.py", line 173, in evaluate self._eval_predictions(predictions, img_ids=img_ids) File "/home/SparseR-CNN/detectron2/evaluation/coco_evaluation.py", line 240, in _eval_predictions if len(coco_results) > 0 File "/homeSparseR-CNN/detectron2/evaluation/coco_evaluation.py", line 549, in _evaluate_predictions_on_coco coco_dt = coco_gt.loadRes(coco_results) File "/opt/conda/lib/python3.7/site-packages/pycocotools-2.0.2-py3.7-linux-x86_64.egg/pycocotools/coco.py", line 327, in loadRes 'Results do not correspond to current coco set' AssertionError: Results do not correspond to current coco set

what is wrong?

[henbucuoshanghai]

the first time to evaluate the mode! 'voc_2007_test' is not registered by register_coco_instances. Therefore trying to convert it to COCO format ...
this is the error?

Serializing 4231 elements to byte tensors and concatenating them all ... [01/15 06:36:03 d2.data.common]: Serialized dataset takes 0.01 MiB WARNING [01/15 06:36:03 d2.evaluation.coco_evaluation]: COCO Evaluator instantiated using config, this is deprecated behavior. Please pass in explicit arguments instead. [01/15 06:36:03 d2.evaluation.coco_evaluation]: 'voc_2007_test' is not registered by register_coco_instances. Therefore trying to convert it to COCO format ... WARNING [01/15 06:36:03 d2.data.datasets.coco]: Using previously cached COCO format annotations at './output/inference/voc_2007_test_coco_format.json'. You need to clear the cache file if your dataset has been modified. [01/15 06:36:03 d2.evaluation.evaluator]: Start inference on 41 images [01/15 06:36:03 d2.evaluation.evaluator]: Inference done 11/41. 0.0336 s / img. ETA=0:00:01 [01/15 06:36:04 d2.evaluation.evaluator]: Total inference time: 0:00:01.347139 (0.037421 s / img per device, on 1 devices) [01/15 06:36:04 d2.evaluation.evaluator]: Total inference pure compute time: 0:00:01 (0.033764 s / img per device, on 1 devices) [01/15 06:36:04 d2.evaluation.coco_evaluation]: Preparing results for COCO format ... [01/15 06:36:04 d2.evaluation.coco_evaluation]: Saving results to ./output/inference/coco_instances_results.json [01/15 06:36:04 d2.evaluation.coco_evaluation]: Evaluating predictions with unofficial COCO API... Loading and preparing results... ERROR [01/15 06:36:04 d2.engine.train_loop]: Exception during training:

[PeizeSun]

Hi~ I guess you are not running the experiments on COCO dataset, am I right? Have you fixed this bug?