Module earthvision.models.resisc45.mobilenetv3
Inspired by torchvision.models.mobilenetv3
Expand source code
"""Inspired by torchvision.models.mobilenetv3"""
import torch
from torch import nn
from typing import Any, Callable, List, Optional
from .utils import load_state_dict_from_url
from torchvision.models.mobilenetv3 import MobileNetV3, InvertedResidualConfig, _mobilenet_v3_conf
__all__ = ["MobileNetV3", "mobilenet_v3_large"]
model_urls = {
"mobilenet_v3_large": (
"https://drive.google.com/uc?id=1--_vx4lTMSKmW1X3DS1KXcewXdmBMu-K",
"resisc45_mobilenetv3_large.pth",
)
}
class OurMobileNetV3(MobileNetV3):
def __init__(
self,
inverted_residual_setting: List[InvertedResidualConfig],
last_channel: int,
num_classes: int = 45,
block: Optional[Callable[..., nn.Module]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None,
**kwargs: Any
) -> None:
super().__init__(
inverted_residual_setting,
last_channel,
num_classes=num_classes,
block=block,
norm_layer=norm_layer,
**kwargs
)
def _mobilenet_v3_model(
arch: str,
inverted_residual_setting: List[InvertedResidualConfig],
last_channel: int,
pretrained: bool,
**kwargs: Any
):
model = OurMobileNetV3(inverted_residual_setting, last_channel, **kwargs)
if pretrained:
if model_urls.get(arch, None) is None:
raise ValueError("No checkpoint is available for model type {}".format(arch))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
state_dict = load_state_dict_from_url(model_urls[arch], map_location=device)
model.load_state_dict(state_dict)
return model
def mobilenet_v3_large(
pretrained: bool = False, progress: bool = True, **kwargs: Any
) -> MobileNetV3:
"""
Constructs a large MobileNetV3 architecture from
`"Searching for MobileNetV3" <https://arxiv.org/abs/1905.02244>`_.
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
"""
arch = "mobilenet_v3_large"
inverted_residual_setting, last_channel = _mobilenet_v3_conf(arch, **kwargs)
return _mobilenet_v3_model(arch, inverted_residual_setting, last_channel, pretrained, **kwargs)
Functions
def mobilenet_v3_large(pretrained: bool = False, progress: bool = True, **kwargs: Any) ‑> torchvision.models.mobilenetv3.MobileNetV3
-
Constructs a large MobileNetV3 architecture from
"Searching for MobileNetV3" <https://arxiv.org/abs/1905.02244>
_.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
Expand source code
def mobilenet_v3_large( pretrained: bool = False, progress: bool = True, **kwargs: Any ) -> MobileNetV3: """ Constructs a large MobileNetV3 architecture from `"Searching for MobileNetV3" <https://arxiv.org/abs/1905.02244>`_. 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 """ arch = "mobilenet_v3_large" inverted_residual_setting, last_channel = _mobilenet_v3_conf(arch, **kwargs) return _mobilenet_v3_model(arch, inverted_residual_setting, last_channel, pretrained, **kwargs)
Classes
class MobileNetV3 (inverted_residual_setting: List[torchvision.models.mobilenetv3.InvertedResidualConfig], last_channel: int, num_classes: int = 1000, block: Optional[Callable[..., torch.nn.modules.module.Module]] = None, norm_layer: Optional[Callable[..., torch.nn.modules.module.Module]] = None, **kwargs: Any)
-
Base class for all neural network modules.
Your models should also subclass this class.
Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::
import torch.nn as nn import torch.nn.functional as F class Model(nn.Module): def __init__(self): super(Model, self).__init__() self.conv1 = nn.Conv2d(1, 20, 5) self.conv2 = nn.Conv2d(20, 20, 5) def forward(self, x): x = F.relu(self.conv1(x)) return F.relu(self.conv2(x))
Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:
to
, etc.:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool
MobileNet V3 main class
Args
inverted_residual_setting
:List[InvertedResidualConfig]
- Network structure
last_channel
:int
- The number of channels on the penultimate layer
num_classes
:int
- Number of classes
block
:Optional[Callable[…, nn.Module]]
- Module specifying inverted residual building block for mobilenet
norm_layer
:Optional[Callable[…, nn.Module]]
- Module specifying the normalization layer to use
Expand source code
class MobileNetV3(nn.Module): def __init__( self, inverted_residual_setting: List[InvertedResidualConfig], last_channel: int, num_classes: int = 1000, block: Optional[Callable[..., nn.Module]] = None, norm_layer: Optional[Callable[..., nn.Module]] = None, **kwargs: Any ) -> None: """ MobileNet V3 main class Args: inverted_residual_setting (List[InvertedResidualConfig]): Network structure last_channel (int): The number of channels on the penultimate layer num_classes (int): Number of classes block (Optional[Callable[..., nn.Module]]): Module specifying inverted residual building block for mobilenet norm_layer (Optional[Callable[..., nn.Module]]): Module specifying the normalization layer to use """ super().__init__() if not inverted_residual_setting: raise ValueError("The inverted_residual_setting should not be empty") elif not (isinstance(inverted_residual_setting, Sequence) and all([isinstance(s, InvertedResidualConfig) for s in inverted_residual_setting])): raise TypeError("The inverted_residual_setting should be List[InvertedResidualConfig]") if block is None: block = InvertedResidual if norm_layer is None: norm_layer = partial(nn.BatchNorm2d, eps=0.001, momentum=0.01) layers: List[nn.Module] = [] # building first layer firstconv_output_channels = inverted_residual_setting[0].input_channels layers.append(ConvNormActivation(3, firstconv_output_channels, kernel_size=3, stride=2, norm_layer=norm_layer, activation_layer=nn.Hardswish)) # building inverted residual blocks for cnf in inverted_residual_setting: layers.append(block(cnf, norm_layer)) # building last several layers lastconv_input_channels = inverted_residual_setting[-1].out_channels lastconv_output_channels = 6 * lastconv_input_channels layers.append(ConvNormActivation(lastconv_input_channels, lastconv_output_channels, kernel_size=1, norm_layer=norm_layer, activation_layer=nn.Hardswish)) self.features = nn.Sequential(*layers) self.avgpool = nn.AdaptiveAvgPool2d(1) self.classifier = nn.Sequential( nn.Linear(lastconv_output_channels, last_channel), nn.Hardswish(inplace=True), nn.Dropout(p=0.2, inplace=True), nn.Linear(last_channel, num_classes), ) for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out') if m.bias is not None: nn.init.zeros_(m.bias) elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)): nn.init.ones_(m.weight) nn.init.zeros_(m.bias) elif isinstance(m, nn.Linear): nn.init.normal_(m.weight, 0, 0.01) nn.init.zeros_(m.bias) def _forward_impl(self, x: Tensor) -> Tensor: x = self.features(x) x = self.avgpool(x) x = torch.flatten(x, 1) x = self.classifier(x) return x def forward(self, x: Tensor) -> Tensor: return self._forward_impl(x)
Ancestors
- torch.nn.modules.module.Module
Subclasses
- earthvision.models.resisc45.mobilenetv3.OurMobileNetV3
- torchvision.models.quantization.mobilenetv3.QuantizableMobileNetV3
Class variables
var dump_patches : bool
var training : bool
Methods
def forward(self, x: torch.Tensor) ‑> torch.Tensor
-
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the :class:
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.Expand source code
def forward(self, x: Tensor) -> Tensor: return self._forward_impl(x)