EterHF
commented
2 months ago Excuse me, I failed to unzip the dataset when I tried to merge the train dataset split file using unzip command in Linux. I also tried unzip -F and export export UNZIP_DISABLE_ZIPBOMB_DETECTION=TRUE, but none worked for me. Can u please tell me how u manage the dataset?
Hi,
We are reaching the following issue when downloading the pre-trained model:
Traceback (most recent call last): File "net_train_multiview.py", line 121, in <module> model = PanopticModel(hparams = hparams, File "/test_MVTrans/MVTrans/src/lib/net/panoptic_trainer.py", line 32, in __init__ self.model = common.get_model(hparams) File "/test_MVTrans/MVTrans/src/lib/net/common.py", line 162, in get_model model = net_attr(hparams) File "/test_MVTrans/MVTrans/model/multiview_net.py", line 268, in res_fpn return MultiviewNet(hparams) File "/test_MVTrans/MVTrans/model/multiview_net.py", line 76, in __init__ self.semanticFeature = ResnetEncoder(resnet, "pretrained") # the features after bn and relu File "/test_MVTrans/MVTrans/model/networks/resnet_encoder.py", line 35, in __init__ self.encoder = resnets[num_layers](pretrained) File "/env/lib/python3.8/site-packages/torchvision/models/_utils.py", line 142, in wrapper return fn(*args, **kwargs) File "/env/lib/python3.8/site-packages/torchvision/models/_utils.py", line 228, in inner_wrapper return builder(*args, **kwargs) File "/env/lib/python3.8/site-packages/torchvision/models/resnet.py", line 761, in resnet50 weights = ResNet50_Weights.verify(weights) File "/env/lib/python3.8/site-packages/torchvision/models/_api.py", line 81, in verify obj = cls[obj.replace(cls.__name__ + ".", "")] File "/env/lib/python3.8/enum.py", line 387, in __getitem__ return cls._member_map_[name] KeyError: 'pretrained'Could you help us debug the problem?
Thanks!