TypeError: 'tuple' object is not callable

[halfslicestudio]

Describe the bug
Everything runs up until the point of trying to actually train then i get the error in the title "TypeError: 'tuple' object is not callable"

To Reproduce
Start training with a custom dataset 256x256

ERROR

Traceback (most recent call last):
File "stylegan3/train.py", line 286, in
main() # pylint: disable=no-value-for-parameter
File "/usr/lib/python3/dist-packages/click/core.py", line 764, in call
return self.main(*args, **kwargs)
File "/usr/lib/python3/dist-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/usr/lib/python3/dist-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/usr/lib/python3/dist-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "stylegan3/train.py", line 281, in main
launch_training(c=c, desc=desc, outdir=opts.outdir, dry_run=opts.dry_run)
File "stylegan3/train.py", line 96, in launch_training
subprocess_fn(rank=0, c=c, temp_dir=temp_dir)
File "stylegan3/train.py", line 47, in subprocess_fn
training_loop.training_loop(rank=rank, **c)
File "/home/ubuntu/ai4/stylegan3/training/training_loop.py", line 278, in training_loop
loss.accumulate_gradients(phase=phase.name, real_img=real_img, real_c=real_c, gen_z=gen_z, gen_c=gen_c, gain=phase.interval, cur_nimg=cur_nimg)
File "/home/ubuntu/ai4/stylegan3/training/loss.py", line 81, in accumulate_gradients
loss_Gmain.mean().mul(gain).backward()
File "/usr/local/lib/python3.8/dist-packages/torch/_tensor.py", line 396, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/usr/local/lib/python3.8/dist-packages/torch/autograd/init.py", line 173, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
File "/usr/local/lib/python3.8/dist-packages/torch/autograd/function.py", line 253, in apply
return user_fn(self, *args)
File "/home/ubuntu/ai4/stylegan3/torch_utils/ops/grid_sample_gradfix.py", line 52, in backward
grad_input, grad_grid = _GridSample2dBackward.apply(grad_output, input, grid)
File "/home/ubuntu/ai4/stylegan3/torch_utils/ops/grid_sample_gradfix.py", line 63, in forward
grad_input, grad_grid = op(grad_output, input, grid, 0, 0, False, output_mask)
TypeError: 'tuple' object is not callable

[Zhuo-Feng]

Hello, you may try pytorchversion==1.10.0 to solve this problem. The code is: !pip install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio===0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html

[hai-kreate]

Another potential fix is to extract op correctly in your local setup:

-op = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')
+op, _ = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')

[hamediut]

Another potential fix is to extract op correctly in your local setup:

-op = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')
+op, _ = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')

This worked for me in Pytorch 1.12.0, thank you :)

[exceedzhang]

Hello, you may try pytorchversion==1.10.0 to solve this problem. The code is: !pip install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio===0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html

The system runs normally after reinstalling pytorch version 1.10.0. thank you!

CUDA 11.3

conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge

[benx13]

Another potential fix is to extract op correctly in your local setup:

-op = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')
+op, _ = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')

This fixed it for me torch== 1.13.1
Thanks.

[xfiax]

Another potential fix is to extract op correctly in your local setup:

-op = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')
+op, _ = torch._C._jit_get_operation('aten::grid_sampler_2d_backward')

hi, i'm using colab. how could I apply this method? I tried the install cuda 1.10.0, it doesn't solve the issue for me.

[jannehellsten]

Should be fixed by c233a91. Sorry for the inconvenience.

[changbuyuan]

您好，您可以嘗試使用 pytorchversion==1.10.0 來解決這個問題。程式碼是：!pip install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio===0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html

Sorry, I used this method and re-ran train.py, but the same error feedback still appeared.

Traceback (most recent call last): File "/content/drive/MyDrive/colab-sg3/stylegan3/train.py", line 317, in <module> main() # pylint: disable=no-value-for-parameter File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1157, in __call__ return self.main(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1078, in main rv = self.invoke(ctx) File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1434, in invoke return ctx.invoke(self.callback, **ctx.params) File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 783, in invoke return __callback(*args, **kwargs) File "/content/drive/MyDrive/colab-sg3/stylegan3/train.py", line 312, in main launch_training(c=c, desc=desc, outdir=opts.outdir, dry_run=opts.dry_run) File "/content/drive/MyDrive/colab-sg3/stylegan3/train.py", line 97, in launch_training subprocess_fn(rank=0, c=c, temp_dir=temp_dir) File "/content/drive/MyDrive/colab-sg3/stylegan3/train.py", line 48, in subprocess_fn training_loop.training_loop(rank=rank, **c) File "/content/drive/MyDrive/colab-sg3/stylegan3/training/training_loop.py", line 279, in training_loop loss.accumulate_gradients(phase=phase.name, real_img=real_img, real_c=real_c, gen_z=gen_z, gen_c=gen_c, gain=phase.interval, cur_nimg=cur_nimg) File "/content/drive/MyDrive/colab-sg3/stylegan3/training/loss.py", line 81, in accumulate_gradients loss_Gmain.mean().mul(gain).backward() File "/usr/local/lib/python3.10/dist-packages/torch/_tensor.py", line 487, in backward torch.autograd.backward( File "/usr/local/lib/python3.10/dist-packages/torch/autograd/__init__.py", line 200, in backward Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass File "/usr/local/lib/python3.10/dist-packages/torch/autograd/function.py", line 274, in apply return user_fn(self, *args) File "/content/drive/MyDrive/colab-sg3/stylegan3/torch_utils/ops/grid_sample_gradfix.py", line 50, in backward grad_input, grad_grid = _GridSample2dBackward.apply(grad_output, input, grid) File "/usr/local/lib/python3.10/dist-packages/torch/autograd/function.py", line 506, in apply return super().apply(*args, **kwargs) # type: ignore[misc] File "/content/drive/MyDrive/colab-sg3/stylegan3/torch_utils/ops/grid_sample_gradfix.py", line 59, in forward grad_input, grad_grid = op(grad_output, input, grid, 0, 0, False) TypeError: 'tuple' object is not callable