Pytorch: AttributeError: cannot assign module before Module.init() call even if initialized

Question

I'm getting the following error:

AttributeError: cannot assign module before Module.init() call

I'm trying to create an instance of my class :

class ResNetGenerator(nn.Module):
    def __init__(self, input_nc=3, output_nc=3, n_residual_blocks=9, use_dropout=False):
        # super(ResNetGenerator, self).__init__()
        super().__init__()

I'm calling super().__init__() but in vain.

What I am doing wrong here?

Complete Traceback:

File "train.py", line 40, in <module>
    model = ColorizationCycleGAN(args)
File "/path/cycle_gan.py", line 27, in __init__
    self.G_A2B = ResNetGenerator(input_nc=self.input_nc, output_nc=self.output_nc, n_residual_blocks=9, use_dropout=False)
File "/path/.local/lib/python3.6/site packages/torch/nn/modules/module.py", line 544, in __setattr__
    "cannot assign module before Module.__init__() call")
AttributeError: cannot assign module before Module.__init__() call

schlodinger · Accepted Answer · 2019-01-05 21:51:05Z

4

In fact, I realized that i wasn't calling super().__init__() in the main class ColorizationCycleGAN. Adding this solved the problem.

I hope that this answer will have the effect of reminding you to check to call the super().__init__() function in all classes that inherits from nn.Module.

answered Jan 5, 2019 at 21:51

schlodinger

5594 silver badges14 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Pytorch: AttributeError: cannot assign module before Module.init() call even if initialized

What I am doing wrong here?

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

What I am doing wrong here?

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related