def _update_default_model_kwargs()

in timm/models/_builder.py [0:0]

• 24 lines of code
• 13 McCabe index (conditional complexity)

def _update_default_model_kwargs(pretrained_cfg, kwargs, kwargs_filter) -> None:
    """ Update the default_cfg and kwargs before passing to model

    Args:
        pretrained_cfg: input pretrained cfg (updated in-place)
        kwargs: keyword args passed to model build fn (updated in-place)
        kwargs_filter: keyword arg keys that must be removed before model __init__
    """
    # Set model __init__ args that can be determined by default_cfg (if not already passed as kwargs)
    default_kwarg_names = ('num_classes', 'global_pool', 'in_chans')
    if pretrained_cfg.get('fixed_input_size', False):
        # if fixed_input_size exists and is True, model takes an img_size arg that fixes its input size
        default_kwarg_names += ('img_size',)

    for n in default_kwarg_names:
        # for legacy reasons, model __init__args uses img_size + in_chans as separate args while
        # pretrained_cfg has one input_size=(C, H ,W) entry
        if n == 'img_size':
            input_size = pretrained_cfg.get('input_size', None)
            if input_size is not None:
                assert len(input_size) == 3
                kwargs.setdefault(n, input_size[-2:])
        elif n == 'in_chans':
            input_size = pretrained_cfg.get('input_size', None)
            if input_size is not None:
                assert len(input_size) == 3
                kwargs.setdefault(n, input_size[0])
        elif n == 'num_classes':
            default_val = pretrained_cfg.get(n, None)
            # if default is < 0, don't pass through to model
            if default_val is not None and default_val >= 0:
                kwargs.setdefault(n, pretrained_cfg[n])
        else:
            default_val = pretrained_cfg.get(n, None)
            if default_val is not None:
                kwargs.setdefault(n, pretrained_cfg[n])

    # Filter keyword args for task specific model variants (some 'features only' models, etc.)
    _filter_kwargs(kwargs, names=kwargs_filter)