RuntimeError

[tbrsvn]

The model starts loading, but on summoning checkpoint this happens.

File "/home/ady/Desktop/toma/stable-diffusion/main.py", line 830, in trainer.fit(model, data) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 740, in fit self._call_and_handle_interrupt( File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 685, in _call_and_handle_interrupt return trainer_fn(*args, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 777, in _fit_impl self._run(model, ckpt_path=ckpt_path) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1199, in _run self._dispatch() File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1279, in _dispatch self.training_type_plugin.start_training(self) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 202, in start_training self._results = trainer.run_stage() File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1289, in run_stage return self._run_train() File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1311, in _run_train self._run_sanity_check(self.lightning_module) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1375, in _run_sanity_check self._evaluation_loop.run() File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/loops/base.py", line 145, in run self.advance(*args, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 110, in advance dl_outputs = self.epoch_loop.run(dataloader, dataloader_idx, dl_max_batches, self.num_dataloaders) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/loops/base.py", line 145, in run self.advance(*args, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 122, in advance output = self._evaluation_step(batch, batch_idx, dataloader_idx) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 217, in _evaluation_step output = self.trainer.accelerator.validation_step(step_kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/accelerators/accelerator.py", line 236, in validation_step return self.training_type_plugin.validation_step(*step_kwargs.values()) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/plugins/training_type/ddp.py", line 444, in validation_step return self.model(*args, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1156, in forward output = self._run_ddp_forward(*inputs, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1110, in _run_ddp_forward return module_to_run(*inputs[0], **kwargs[0]) # type: ignore[index] File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/pytorch_lightning/overrides/base.py", line 92, in forward output = self.module.validation_step(*inputs, **kwargs) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/home/ady/Desktop/toma/stable-diffusion/ldm/models/diffusion/ddpm.py", line 368, in validation_step _, loss_dict_no_ema = self.shared_step(batch) File "/home/ady/Desktop/toma/stable-diffusion/ldm/models/diffusion/ddpm.py", line 908, in shared_step loss = self(x, c) File "/home/ady/Desktop/toma/toma/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/ady/Desktop/toma/stable-diffusion/ldm/models/diffusion/ddpm.py", line 942, in forward return self.p_losses(x, c, t, *args, **kwargs) File "/home/ady/Desktop/toma/stable-diffusion/ldm/models/diffusion/ddpm.py", line 1093, in p_losses logvar_t = self.logvar[t].to(self.device) RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

What should I do to fix this?

[shoutOutYangJie]

I meet the same error

[cifang-Kasit]

same

[yy13138]

same error， how to do..

[zmj1203]

I modify the code and then it can run (I am not sure, you can try it.) File "/home/ady/Desktop/toma/stable-diffusion/ldm/models/diffusion/ddpm.py", line 1093, in p_losses logvar_t = self.logvar[t].to(self.device) -> logvar_t = self.logvar[t.cpu()].to(self.device)