PyDev console: starting. Python 3.8.16 (default, Jun 12 2023, 21:00:42) [MSC v.1916 64 bit (AMD64)] [iObjectsPy]: The Gateway service started successfully Training Data is inited! If the backbone's weight download fails, please download it from the following URL and save it to the directory "D:\Supermap\resources_ml\backbone" or "C:\Users\86138/.cache\torch\checkpoints". The download URL is:
https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b3-5fb5a3c3.pth Downloading: "
https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b3-5fb5a3c3.pth" to C:\Users\86138/.cache\torch\hub\checkpoints\efficientnet-b3-5fb5a3c3.pth Traceback (most recent call last): File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\_torch_models\encoders\__init__.py", line 71, in load_weighs_url File "D:\SuperMap iDesktopX 11i(2024)\产品包\supermap-idesktopx-11.2.0-windows-x64-bin\supermap-idesktopx-ext_ai-11.2.0-windows-x64-bin\support\MiniConda\conda\lib\site-packages\torch\hub.py", line 750, in load_state_dict_from_url return torch.load(cached_file, map_location=map_location) File "D:\SuperMap iDesktopX 11i(2024)\产品包\supermap-idesktopx-11.2.0-windows-x64-bin\supermap-idesktopx-ext_ai-11.2.0-windows-x64-bin\support\MiniConda\conda\lib\site-packages\torch\serialization.py", line 815, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "D:\SuperMap iDesktopX 11i(2024)\产品包\supermap-idesktopx-11.2.0-windows-x64-bin\supermap-idesktopx-ext_ai-11.2.0-windows-x64-bin\support\MiniConda\conda\lib\site-packages\torch\serialization.py", line 1051, in _legacy_load typed_storage._untyped_storage._set_from_file( RuntimeError: unexpected EOF, expected 215549 more bytes. The file might be corrupted. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "", line 1, in File "D:\Supermap\resources\python-helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile pydev_imports.execfile(filename, global_vars, local_vars) # execute the script File "D:\Supermap\resources\python-helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "C:\Users\86138\AppData\Local\Temp\model_train_3.py", line 11, in ImageryTrainer(train_data_path=r"E:\training_data",config=r"D:\SuperMap iDesktopX 11i(2024)\产品包\supermap-idesktopx-11.2.0-windows-x64-bin\supermap-idesktopx-ext_ai-11.2.0-windows-x64-bin\resources_ml\trainer_config\multi_classification\multi_cls_unet.sdt",epoch=int(10),batch_size=int(1),lr=None,output_model_path=r"E:\实验数据\模型",output_model_name=r"saved_model_1",backbone_name=r"efficientnet-b3",backbone_weight_path=None,log_path=r"E:\训练日志\checkpoints",reload_model=False,pretrained_model_path=None,gpus=[0]).multi_classify_train() File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_trainer.py", line 111, in multi_classify_train File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_trainer_collector\binary_classification_train.py", line 37, in train File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_trainer_collector\binary_classification_train.py", line 65, in unet_pytorch File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\_torch_models\geo_api\train_api.py", line 103, in train File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\_torch_models\geo_api\train_api.py", line 236, in main_worker File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\unet_torch.py", line 24, in get_model File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\_torch_models\geo_api\model_builder.py", line 31, in build_torch_seg_model File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\_torch_models\unet\model.py", line 62, in __init__ File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\_torch_models\encoders\__init__.py", line 50, in get_encoder File "I:\teamctiy\BuildAgent\work\test_trunk/iobjectspy/ml\vision\_models\semantic_seg\_torch_models\encoders\__init__.py", line 73, in load_weighs_url ConnectionError: Backbone weight files download failed! 您好，遥感影像模型训练时一直出错，能看一下是什么问题吗？谢谢！
