The exception will happen as below.
I tried the other two models: HRNetW32-1S.pth and HRNetW48-5S-FPN-2.pth, unfortunately, none of them run successfully.
[08/12 12:44:27 fvcore.common.checkpoint]: [Checkpointer] Loading from output/ResNet50-4S-FPN-2.pth ...
Traceback (most recent call last):
File "tools/train_net.py", line 160, in
args=(args,),
File "d:\dataset\src\detectron2\detectron2\engine\launch.py", line 62, in launch
main_func(*args)
File "tools/train_net.py", line 130, in main
res = Trainer.test(cfg, model)
File "d:\dataset\src\detectron2\detectron2\engine\defaults.py", line 512, in test
data_loader = cls.build_test_loader(cfg, dataset_name)
File "tools/train_net.py", line 58, in build_test_loader
return build_detection_test_loader(cfg, dataset_name, mapper=DatasetMapper(cfg, False))
File "d:\dataset\src\detectron2\detectron2\data\build.py", line 382, in build_detection_test_loader
else None,
File "d:\dataset\src\detectron2\detectron2\data\build.py", line 219, in get_detection_dataset_dicts
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "d:\dataset\src\detectron2\detectron2\data\build.py", line 219, in
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "d:\dataset\src\detectron2\detectron2\data\catalog.py", line 58, in get
return f()
File "D:\code\newton\workspace\pytorchPro\VisionFormer\stgraph\SceneGraph\fcsgg\fcsgg\data\datasets\visual_genome.py", line 491, in
filter_non_overlap=False))
File "D:\code\newton\workspace\pytorchPro\VisionFormer\stgraph\SceneGraph\fcsgg\fcsgg\data\datasets\visual_genome.py", line 401, in get_dicts
filenames = [self.all_filenames[i] for i in np.where(split_mask)[0]]
File "D:\code\newton\workspace\pytorchPro\VisionFormer\stgraph\SceneGraph\fcsgg\fcsgg\data\datasets\visual_genome.py", line 401, in
filenames = [self.all_filenames[i] for i in np.where(split_mask)[0]]
IndexError: list index out of range
LeonLee8Hang
commented
2 years ago
Hi, I downloaded the pre-trained model as mentioned and run the command as below:
python tools/train_net.py --eval-only --config-file configs/eval/FCSGG-Res50-BiFPN-P2P5-MultiscaleHead-MS.yaml MODEL.WEIGHTS "output/ResNet50-4S-FPN-2.pth"
The exception will happen as below. I tried the other two models: HRNetW32-1S.pth and HRNetW48-5S-FPN-2.pth, unfortunately, none of them run successfully.
[08/12 12:44:27 fvcore.common.checkpoint]: [Checkpointer] Loading from output/ResNet50-4S-FPN-2.pth ... Traceback (most recent call last): File "tools/train_net.py", line 160, in
args=(args,),
File "d:\dataset\src\detectron2\detectron2\engine\launch.py", line 62, in launch
main_func(*args)
File "tools/train_net.py", line 130, in main
res = Trainer.test(cfg, model)
File "d:\dataset\src\detectron2\detectron2\engine\defaults.py", line 512, in test
data_loader = cls.build_test_loader(cfg, dataset_name)
File "tools/train_net.py", line 58, in build_test_loader
return build_detection_test_loader(cfg, dataset_name, mapper=DatasetMapper(cfg, False))
File "d:\dataset\src\detectron2\detectron2\data\build.py", line 382, in build_detection_test_loader
else None,
File "d:\dataset\src\detectron2\detectron2\data\build.py", line 219, in get_detection_dataset_dicts
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "d:\dataset\src\detectron2\detectron2\data\build.py", line 219, in
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "d:\dataset\src\detectron2\detectron2\data\catalog.py", line 58, in get
return f()
File "D:\code\newton\workspace\pytorchPro\VisionFormer\stgraph\SceneGraph\fcsgg\fcsgg\data\datasets\visual_genome.py", line 491, in
filter_non_overlap=False))
File "D:\code\newton\workspace\pytorchPro\VisionFormer\stgraph\SceneGraph\fcsgg\fcsgg\data\datasets\visual_genome.py", line 401, in get_dicts
filenames = [self.all_filenames[i] for i in np.where(split_mask)[0]]
File "D:\code\newton\workspace\pytorchPro\VisionFormer\stgraph\SceneGraph\fcsgg\fcsgg\data\datasets\visual_genome.py", line 401, in
filenames = [self.all_filenames[i] for i in np.where(split_mask)[0]]
IndexError: list index out of range