style-based-gan-pytorch
style-based-gan-pytorch copied to clipboard
Published
20 hours ago •
rosinality
rosinality
TypeError: forward() missing 1 required positional argument: 'input'
> CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 train.py --mixing --loss r1 --sched --phase 16 train-full
Size: 256; G: 2.811; D: 3.419; Grad: 0.003; Alpha: 1.00000: 0%| | 13/3000000 [01:08<17:22:00, 2.08s/it]Traceback (most recent call last):
File "train_v3.py", line 345, in <module>
train(args, dataset, generator, discriminator)
File "train_v3.py", line 133, in train
real_scores = discriminator(real_image, step=step, alpha=alpha)
File "/home/michael/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/home/michael/.local/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 152, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/home/michael/.local/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 162, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/home/michael/.local/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 85, in parallel_apply
output.reraise()
File "/home/michael/.local/lib/python3.6/site-packages/torch/_utils.py", line 369, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in replica 4 on device 4.
Original Traceback (most recent call last):
File "/home/michael/.local/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker
output = module(*input, **kwargs)
File "/home/michael/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
TypeError: forward() missing 1 required positional argument: 'input'
Size: 256; G: 2.811; D: 3.419; Grad: 0.003; Alpha: 1.00000: 0%| | 13/3000000 [01:14<48:01:02, 5.76s/it]
Same issue, you could try adding drop_last=True in Dataloader in sample_data function in train.py
