RuntimeError: weight tensor should be defined either for all 19 classes or no classes but got weight tensor of shape: [1, 19]

Question

RuntimeError: weight tensor should be defined either for all 19 classes or no classes but got weight tensor of shape: [1, 19]

pomeloooo opened this issue a year ago · comments

RuntimeError: weight tensor should be defined either for all 19 classes or no classes but got weight tensor of shape: [1, 19]
how to solve

magical1998 · Answer 1 · Thu Jun 01 2023 18:00:52 GMT+0800 (China Standard Time)

I have same error，have u solve it？

magical1998 · Answer 2 · Fri Jun 02 2023 08:55:05 GMT+0800 (China Standard Time)

weight‘s shape should be (19,),not (1,19)
in train_SemantciKITTI.py，line 94

    class_weights = torch.from_numpy(train_dataset.get_class_weight()).float().cuda()
    class_weights=class_weights.squeeze(0)
    self.criterion = nn.CrossEntropyLoss(weight=class_weights, reduction='none')

Wansit Hepburn · Answer 3 · Mon Oct 16 2023 17:23:57 GMT+0800 (China Standard Time)

weight‘s shape should be (19,),not (1,19) in train_SemantciKITTI.py，line 94

    class_weights = torch.from_numpy(train_dataset.get_class_weight()).float().cuda()
    class_weights=class_weights.squeeze(0)
    self.criterion = nn.CrossEntropyLoss(weight=class_weights, reduction='none')

    class_weights = torch.from_numpy(train_dataset.get_class_weight()).float().view(19).cuda() # change code to this can run