Error in 02-Pixel-Diffusion-colab.ipynb

[yoloshoko]

B=8 # number of samples
STEPS=200 # ddim steps

ddim_sampler=DDIM_Sampler(STEPS,model.model.num_timesteps)

model.cuda()
out=model(batch_size=B,sampler=ddim_sampler,shape=(64,64),verbose=True)

I encountered an error when running the code above. The error is as follows:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[12], [line 7](vscode-notebook-cell:?execution_count=12&line=7)
      4 ddim_sampler=DDIM_Sampler(STEPS,model.model.num_timesteps)
      6 model.cuda()
----> [7](vscode-notebook-cell:?execution_count=12&line=7) out=model(batch_size=B,sampler=ddim_sampler,shape=(64,64),verbose=True)

File f:\develop\anaconda\envs\py312-pytorch12\Lib\site-packages\torch\nn\modules\module.py:1736, in Module._wrapped_call_impl(self, *args, **kwargs)
   1734     return self._compiled_call_impl(*args, **kwargs)  # type: ignore[misc]
   1735 else:
-> [1736](file:///F:/develop/anaconda/envs/py312-pytorch12/Lib/site-packages/torch/nn/modules/module.py:1736)     return self._call_impl(*args, **kwargs)

File f:\develop\anaconda\envs\py312-pytorch12\Lib\site-packages\torch\nn\modules\module.py:1747, in Module._call_impl(self, *args, **kwargs)
   1742 # If we don't have any hooks, we want to skip the rest of the logic in
   1743 # this function, and just call forward.
   1744 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
   1745         or _global_backward_pre_hooks or _global_backward_hooks
   1746         or _global_forward_hooks or _global_forward_pre_hooks):
-> [1747](file:///F:/develop/anaconda/envs/py312-pytorch12/Lib/site-packages/torch/nn/modules/module.py:1747)     return forward_call(*args, **kwargs)
   1749 result = None
   1750 called_always_called_hooks = set()

File f:\develop\anaconda\envs\py312-pytorch12\Lib\site-packages\torch\utils\_contextlib.py:116, in context_decorator.<locals>.decorate_context(*args, **kwargs)
    113 @functools.wraps(func)
    114 def decorate_context(*args, **kwargs):
...
-> [1931](file:///F:/develop/anaconda/envs/py312-pytorch12/Lib/site-packages/torch/nn/modules/module.py:1931) raise AttributeError(
   1932     f"'{type(self).__name__}' object has no attribute '{name}'"
   1933 )

AttributeError: 'DDIM_Sampler' object has no attribute 'alphas_cumprod_prev_sqrt'
Output is truncated. View as a [scrollable element](command:cellOutput.enableScrolling?fa2cab4c-666a-42ae-839f-75132ed1ebf6) or open in a [text editor](command:workbench.action.openLargeOutput?fa2cab4c-666a-42ae-839f-75132ed1ebf6). Adjust cell output [settings](command:workbench.action.openSettings?%5B%22%40tag%3AnotebookOutputLayout%22%5D)...