def _gen_fbnetv3()

in timm/models/mobilenetv3.py [0:0]

• 54 lines of code
• 4 McCabe index (conditional complexity)

def _gen_fbnetv3(variant: str, channel_multiplier: float = 1.0, pretrained: bool = False, **kwargs) -> MobileNetV3:
    """FBNetV3 model generator.

    Paper: `FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining`
        - https://arxiv.org/abs/2006.02049
    FIXME untested, this is a preliminary impl of some FBNet-V3 variants.

    Args:
        variant: Model variant name.
        channel_multiplier: Channel width multiplier.
        pretrained: Load pretrained weights.
        **kwargs: Additional model arguments.

    Returns:
        MobileNetV3 model instance.
    """
    vl = variant.split('_')[-1]
    if vl in ('a', 'b'):
        stem_size = 16
        arch_def = [
            ['ds_r2_k3_s1_e1_c16'],
            ['ir_r1_k5_s2_e4_c24', 'ir_r3_k5_s1_e2_c24'],
            ['ir_r1_k5_s2_e5_c40_se0.25', 'ir_r4_k5_s1_e3_c40_se0.25'],
            ['ir_r1_k5_s2_e5_c72', 'ir_r4_k3_s1_e3_c72'],
            ['ir_r1_k3_s1_e5_c120_se0.25', 'ir_r5_k5_s1_e3_c120_se0.25'],
            ['ir_r1_k3_s2_e6_c184_se0.25', 'ir_r5_k5_s1_e4_c184_se0.25', 'ir_r1_k5_s1_e6_c224_se0.25'],
            ['cn_r1_k1_s1_c1344'],
        ]
    elif vl == 'd':
        stem_size = 24
        arch_def = [
            ['ds_r2_k3_s1_e1_c16'],
            ['ir_r1_k3_s2_e5_c24', 'ir_r5_k3_s1_e2_c24'],
            ['ir_r1_k5_s2_e4_c40_se0.25', 'ir_r4_k3_s1_e3_c40_se0.25'],
            ['ir_r1_k3_s2_e5_c72', 'ir_r4_k3_s1_e3_c72'],
            ['ir_r1_k3_s1_e5_c128_se0.25', 'ir_r6_k5_s1_e3_c128_se0.25'],
            ['ir_r1_k3_s2_e6_c208_se0.25', 'ir_r5_k5_s1_e5_c208_se0.25', 'ir_r1_k5_s1_e6_c240_se0.25'],
            ['cn_r1_k1_s1_c1440'],
        ]
    elif vl == 'g':
        stem_size = 32
        arch_def = [
            ['ds_r3_k3_s1_e1_c24'],
            ['ir_r1_k5_s2_e4_c40', 'ir_r4_k5_s1_e2_c40'],
            ['ir_r1_k5_s2_e4_c56_se0.25', 'ir_r4_k5_s1_e3_c56_se0.25'],
            ['ir_r1_k5_s2_e5_c104', 'ir_r4_k3_s1_e3_c104'],
            ['ir_r1_k3_s1_e5_c160_se0.25', 'ir_r8_k5_s1_e3_c160_se0.25'],
            ['ir_r1_k3_s2_e6_c264_se0.25', 'ir_r6_k5_s1_e5_c264_se0.25', 'ir_r2_k5_s1_e6_c288_se0.25'],
            ['cn_r1_k1_s1_c1728'],
        ]
    else:
        raise NotImplemented
    round_chs_fn = partial(round_channels, multiplier=channel_multiplier, round_limit=0.95)
    se_layer = partial(SqueezeExcite, gate_layer='hard_sigmoid', rd_round_fn=round_chs_fn)
    act_layer = resolve_act_layer(kwargs, 'hard_swish')
    model_kwargs = dict(
        block_args=decode_arch_def(arch_def),
        num_features=1984,
        head_bias=False,
        stem_size=stem_size,
        round_chs_fn=round_chs_fn,
        se_from_exp=False,
        norm_layer=partial(nn.BatchNorm2d, **resolve_bn_args(kwargs)),
        act_layer=act_layer,
        se_layer=se_layer,
        **kwargs,
    )
    model = _create_mnv3(variant, pretrained, **model_kwargs)
    return model