How to export predicted result in aneurysm3D example

[syusaku625]

No description provided.

[rezaakb]

If you use our package directly, you can access predictions as described in the tutorial. However, you raise a good point, and we will add it to the package for use with the Hydra config file.

preds_list = trainer.predict(model=model, datamodule=datamodule)
preds_dict = pinnstorch.utils.fix_predictions(preds_list)

[syusaku625]

I tried to export predicted data following your advice, but I got following errors.
Please give me advise how to solve this error.

Traceback (most recent call last):
File "/home/shusaku/pinns-torch/examples/aneurysm3D/train.py", line 169, in main
metric_dict, _ = pinnstorch.train(
File "/home/shusaku/pinns-torch/pinnstorch/utils/utils.py", line 85, in wrap
raise ex
File "/home/shusaku/pinns-torch/pinnstorch/utils/utils.py", line 73, in wrap
metric_dict, object_dict = task_func(
File "/home/shusaku/pinns-torch/pinnstorch/train.py", line 174, in train
preds_list = trainer.predict(
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 864, in predict
return call._call_and_handle_interrupt(
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 44, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 903, in _predict_impl
results = self._run(model, ckpt_path=ckpt_path)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run
results = self._run_stage()
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1030, in _run_stage
return self.predict_loop.run()
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/loops/utilities.py", line 182, in _decorator
return loop_run(self, *args, **kwargs)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/loops/prediction_loop.py", line 122, in run
self._predict_step(batch, batch_idx, dataloader_idx, dataloader_iter)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/loops/prediction_loop.py", line 228, in _predict_step
batch = call._call_strategy_hook(trainer, "batch_to_device", batch, dataloader_idx=dataloader_idx)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook
output = fn(*args, **kwargs)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 269, in batch_to_device
return model._apply_batch_transfer_handler(batch, device=device, dataloader_idx=dataloader_idx)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/core/module.py", line 333, in _apply_batch_transfer_handler
batch = self._call_batch_hook("transfer_batch_to_device", batch, device, dataloader_idx)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/core/module.py", line 322, in _call_batch_hook
return trainer_method(trainer, hook_name, *args)
File "/home/shusaku/pinns-torch/test/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook
output = fn(*args, **kwargs)
File "/home/shusaku/pinns-torch/pinnstorch/models/pinn_module.py", line 241, in transfer_batch_to_device
self.copy_batch(batch)
File "/home/shusaku/pinns-torch/pinnstorch/models/pinn_module.py", line 329, in copy_batch
spatial, time, solution = self.static_batch[key]
TypeError: unhashable type: 'list'

[rezaakb]

Sorry for any inconvenience. We have added a new feature to the package. Now you can add save_pred: true to the config file, and the prediction will be saved in the output directory. Please let me know if you still have issues with saving predictions.