Hi, I'd like to ask, can the type of multiple inputs be a tuple? If I modify assert, will it affect the model results? When I run the program, the following will appear:
AssertionError: Input format misunderstood. Except either dict, list or tensor; while <class 'tuple'> was given.
Will there be any adverse effects on modifying the inputs type in the following function?
def quantize_torch_model(
model: torch.nn.Module,
calib_dataloader: DataLoader,
calib_steps: int,
input_shape: List[int],
platform: TargetPlatform,
input_dtype: torch.dtype = torch.float,
setting: QuantizationSetting = None,
collate_fn: Callable = None,
inputs: List[Any] = None,
do_quantize: bool = True,
onnx_export_file: str = 'onnx.model',
device: str = 'cuda',
verbose: int = 0,
) -> BaseGraph:
Hi, I'd like to ask, can the type of multiple inputs be a tuple? If I modify assert, will it affect the model results? When I run the program, the following will appear:
AssertionError: Input format misunderstood. Except either dict, list or tensor; while <class 'tuple'> was given.
Will there be any adverse effects on modifying the inputs type in the following function?
def quantize_torch_model(
model: torch.nn.Module,
calib_dataloader: DataLoader,
calib_steps: int,
input_shape: List[int],
platform: TargetPlatform,
input_dtype: torch.dtype = torch.float,
setting: QuantizationSetting = None,
collate_fn: Callable = None,
inputs: List[Any] = None,
do_quantize: bool = True,
onnx_export_file: str = 'onnx.model',
device: str = 'cuda',
verbose: int = 0,
) -> BaseGraph: