Error when running the single_pair_inference example

[ahof1704]

Hi,

I am getting the following error when running the inference example using the two provided pdb files:

Traceback (most recent call last):
  File "/root/DiffDock-PP/src/main_inf.py", line 620, in <module>
    main()
  File "/root/DiffDock-PP/src/main_inf.py", line 339, in main
    pred_list = evaluate_confidence(model_confidence,samples_loader,args) # TODO -> maybe list inside
  File "/root/DiffDock-PP/src/main_inf.py", line 61, in evaluate_confidence
    pred = model(data)
  File "/opt/mamba/envs/diffdock_pp/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/DiffDock-PP/src/model/model.py", line 84, in forward
    logits = self.encoder(batch)
  File "/opt/mamba/envs/diffdock_pp/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/DiffDock-PP/src/model/diffusion.py", line 279, in forward
    tr_t = batch.complex_t["tr"]
  File "/opt/mamba/envs/diffdock_pp/lib/python3.10/site-packages/torch_geometric/data/hetero_data.py", line 156, in __getattr__
    raise AttributeError(f"'{self.__class__.__name__}' has no "
AttributeError: 'HeteroDataBatch' has no attribute 'complex_t'

Any ideas on what could be causing the problem?

Potentially relevant info: I am running this code in CPU only for now. So I commented out all the sections that were assigning the model or data to cuda.

Thanks!