Skip to content

Not supported for CPU only machine #12

Description

@ryan-pauling-ai

When the GPU is removed from the VM there is no longer support.
The first issue that arose was:

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

so I edited DSDP_blind_docking.py under DrugMain to now have

            if os.path.exists(model_cache_best):
                if device.type == 'cuda':
                    network = torch.load(model_cache_best).to(device)
                else:
                    network = torch.load(model_cache_best, map_location=torch.device('cpu')).to(device)

However now it just gives
Segmentation Fault after drug discovery >>> is printed.

Please update the code so it works on a CPU only machine with torch

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions