facebookresearch / Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
MIT License
2.59k stars 388 forks source link

Argument 'bb' has incorrect type (expected numpy.ndarray, got list) #139

Open John-chen521 opened 2 years ago

John-chen521 commented 2 years ago

File "Mask2Former/detectron2/engine/train_loop.py", line 150, in train self.after_step() File "detectron2/engine/train_loop.py", line 180, in after_step h.after_step() File "Mask2Former/detectron2/engine/hooks.py", line 555, in after_step self._do_eval() File Mask2Former/detectron2/engine/hooks.py", line 528, in _do_eval results = self._func() File "/Mask2Former/detectron2/engine/defaults.py", line 453, in test_and_save_results self._last_eval_results = self.test(self.cfg, self.model) File "Mask2Former/detectron2/engine/defaults.py", line 617, in test results_i = inference_on_dataset(model, data_loader, evaluator) File "/Mask2Former/detectron2/evaluation/evaluator.py", line 204, in inference_on_dataset results = evaluator.evaluate() File "Mask2Former/detectron2/evaluation/coco_evaluation.py", line 206, in evaluate self._eval_predictions(predictions, img_ids=img_ids) File "Mask2Former/detectron2/evaluation/coco_evaluation.py", line 266, in _eval_predictions _evaluate_predictions_on_coco( File "Mask2Former/detectron2/evaluation/coco_evaluation.py", line 627, in _evaluate_predictions_on_coco coco_eval.evaluate() File "Mask2Former/detectron2/evaluation/fast_eval_api.py", line 40, in evaluate self._prepare() # bottleneck File "/opt/anaconda3/envs/mask2former/lib/python3.8/site-packages/pycocotools-2.0.4-py3.8-linux-x86_64.egg/pycocotools/cocoeval.py", line 104, in _prepare _toMask(gts, self.cocoGt) File "/opt/anaconda3/envs/mask2former/lib/python3.8/site-packages/pycocotools-2.0.4-py3.8-linux-x86_64.egg/pycocotools/cocoeval.py", line 92, in _toMask rle = coco.annToRLE(ann) File "/opt/anaconda3/envs/mask2former/lib/python3.8/site-packages/pycocotools-2.0.4-py3.8-linux-x86_64.egg/pycocotools/coco.py", line 427, in annToRLE rles = maskUtils.frPyObjects(segm, h, w) File "pycocotools/_mask.pyx", line 294, in pycocotools._mask.frPyObjects help me

Rocomla commented 3 weeks ago

I encounter with the same issue,have u solved it?