AttributeError: 'COCODataSet' object has no attribute 'init_anno_cropper'

[alria6917]

问题确认 Search before asking

• [x] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

W:\anaconda3\envs\paddle\python.exe W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\tools\train.py [05/27 23:06:31] ppdet.utils.checkpoint INFO: Skipping import of the encryption module. loading annotations into memory... Done (t=0.00s) creating index... index created! [05/27 23:06:31] ppdet.data.source.coco INFO: Load [68 samples valid, 0 samples invalid] in file W:\work\OSENSINC\limo\data\annotations\instance_train.json. W0527 23:06:32.579996 25196 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.9, Driver API Version: 12.8, Runtime API Version: 12.0 W0527 23:06:32.584482 25196 gpu_resources.cc:164] device: 0, cuDNN Version: 8.8. Traceback (most recent call last): File "W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\tools\train.py", line 212, in main() File "W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\tools\train.py", line 208, in main run(FLAGS, cfg) File "W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\tools\train.py", line 148, in run trainer = Trainer(cfg, mode='train') File "W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\ppdet\engine\trainer.py", line 259, in init self._init_callbacks() File "W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\ppdet\engine\trainer.py", line 275, in _init_callbacks self._callbacks.append(SniperProposalsGenerator(self)) File "W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\ppdet\engine\callbacks.py", line 554, in init self.dataset = self._create_new_dataset(ori_dataset) File "W:\work\OSENSINC\limo\PaddleDetection-release-2.8.1\ppdet\engine\callbacks.py", line 562, in _create_new_dataset dataset.init_anno_cropper() AttributeError: 'COCODataSet' object has no attribute 'init_anno_cropper'

[Sunting78]

try save_proposals=False

[TingquanGao]

The issue has no response for a long time and will be closed. You can reopen or new another issue if are still confused.

---

From Bot