KeyError: 'optimizer'

[Liupei-Luna]

when training，is_finetune = True, it appears KeyError: 'optimizer'

[ewrfcas]

By default, we finetune our model based on previous optimizer weights. If you are using our provided weights without optimizer, you could comment this line. https://github.com/ewrfcas/MVSFormer/blob/a635b1714a51948f6e808766e9dafa73d05ed51a/train.py#L117

[Liupei-Luna]

ok, it also appears, Error line : self.scaler.step(self.optimizer)

assert self._scale is not None, "Attempted {} but _scale is None. ".format(funcname) + fix AssertionError: Attempted step but _scale is None. This may indicate your script did not use scaler.scale(loss or outputs) earlier in the iteration.

[ewrfcas]

Strange problem. If you have set fp16, scaler.scale should be run in https://github.com/ewrfcas/MVSFormer/blob/77abe395cc32844478733e00aed9f73ad40ba05f/trainer/mvsformer_trainer.py#L134-L137

[Liupei-Luna]

the default set is fp16 = true, can it be changed to false if self.fp16: self.scaler.scale(loss).backward() else: loss.backward() this is the same of my code, but the question appears

[ewrfcas]

fp16 could be set to False, which is only used to save memory and speed up the training.

[Zhu980805]

Same error has occured: AssertionError: Attempted step but _scale is None. This may indicate your script did not use scaler.scale(loss or outputs) earlier in the iteration. @Liupei-Luna I would like to ask if the problem has been solved? Thanks. @ewrfcas I use the default config with "config_mvsformer-p.json", only batchsize is changed to 2 (Beacuse i only have 2 RTX 3090 cards with 24GB memory).