def __init__(self, out_channels, stage_idxs, model_name, depth=5, **kwargs):
inverted_residual_setting, last_channel = _mobilenet_v3_conf(model_name, kwargs)
super().__init__(inverted_residual_setting, last_channel, **kwargs)
self._depth = depth
self._stage_idxs = stage_idxs
self._out_channels = out_channels
self._in_channels = 3
del self.classifier
def __init__(self,
in_channels,
width_mult: float = 1.0,
reduced_tail: bool = False,
dilated: bool = False):
super().__init__(in_channels=in_channels,
inverted_residual_setting=_mobilenet_v3_conf(
'mobilenet_v3_large',
width_mult=width_mult,
reduced_tail=reduced_tail,
dilated=dilated)[0])
def mobilenet_v3_small(pretrained=False, progress=True, quantize=False, **kwargs):
"""
Constructs a MobileNetV3 Small architecture from
`"Searching for MobileNetV3" <https://arxiv.org/abs/1905.02244>`_.
Note that quantize = True returns a quantized model with 8 bit
weights. Quantized models only support inference and run on CPUs.
GPU inference is not yet supported
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet.
progress (bool): If True, displays a progress bar of the download to stderr
quantize (bool): If True, returns a quantized model, else returns a float model
"""
arch = "mobilenet_v3_small"
inverted_residual_setting, last_channel = _mobilenet_v3_conf(arch, kwargs)
return _mobilenet_v3_model(arch, inverted_residual_setting, last_channel, pretrained, progress, quantize, **kwargs)