关于aitodv2

[Mr-Bigworth]

请问aitodv2数据和aitodv1的数据只是标注存在差异对不

[Chasel-Tsui]

是的

[Mr-Bigworth]

是的

嗯嗯，那请问config中的small_trainval_v2_2.0.json和small_test_v2_2.0.json是怎样得到的呢，我看aitodv2的链接只提供了aitodv2_train.json和aitodv2_val.json https://drive.google.com/drive/folders/1Er14atDO1cBraBD4DSFODZV1x7NHO_PY

[Mr-Bigworth]

是的

还有想请教一下，您成功运行的pytorch版本是多少呢，1.10+cuda113会如下报错： Traceback (most recent call last): File "tools/train.py", line 188, in main() File "tools/train.py", line 162, in main model.init_weights() File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/mmcv/runner/base_module.py", line 117, in init_weights m.init_weights() File "/share/home/wut_wanghn/rfla/mmdet-rfla/mmdet/models/necks/rfp.py", line 113, in init_weights self.rfp_modules[rfp_idx].init_weights() File "/share/home/wut_wanghn/rfla/mmdet-rfla/mmdet/models/backbones/detectors_resnet.py", line 301, in init_weights load_checkpoint(self, self.pretrained, strict=False, logger=logger) File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/mmcv/runner/checkpoint.py", line 531, in load_checkpoint checkpoint = _load_checkpoint(filename, map_location, logger) File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/mmcv/runner/checkpoint.py", line 470, in _load_checkpoint return CheckpointLoader.load_checkpoint(filename, map_location, logger) File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/mmcv/runner/checkpoint.py", line 249, in load_checkpoint return checkpoint_loader(filename, map_location) File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/mmcv/runner/checkpoint.py", line 383, in load_from_torchvision model_urls = get_torchvision_models() File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/mmcv/runner/checkpoint.py", line 113, in get_torchvision_models _zoo = import_module(f'torchvision.models.{name}') File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/importlib/init.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1006, in _gcd_import File "", line 983, in _find_and_load File "", line 967, in _find_and_load_unlocked File "", line 677, in _load_unlocked File "", line 728, in exec_module File "", line 219, in _call_with_frames_removed File "/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/torchvision/models/convnext.py", line 11, in from ..utils import _log_api_usage_once ImportError: cannot import name '_log_api_usage_once' from 'torchvision.utils' (/share/home/wut_wanghn/.conda/envs/mmdet-rfla/lib/python3.7/site-packages/torchvision/utils.py)

[Mr-Bigworth]

已解决