Module `earthvision.models.resisc45.vgg16`

Expand source code

import torch
from torch import nn
from typing import Any
from torchvision.models import VGG
from torchvision.models.vgg import make_layers, cfgs

from .utils import load_state_dict_from_url


__all__ = ['VGG', 'vgg16']

model_urls = {
    "vgg16": (
        "https://drive.google.com/uc?id=1fxw_aFVAI7Z-XxmFjp-q0XapWyrBMYdA",
        "resisc45_vgg16.pth",
    )
}


class VGG16Resisc45(VGG):
    def __init__(
        self,
        features: nn.Module,
        num_classes: int = 45,
        init_weights: bool = True
    ):
        super().__init__(features, num_classes=num_classes, init_weights=init_weights)


def _vgg(arch: str, cfg: str, batch_norm: bool, pretrained: bool, progress: bool = True, **kwargs: Any) -> VGG16Resisc45:
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG16Resisc45(make_layers(cfgs[cfg], batch_norm=batch_norm), **kwargs)
    if pretrained:
        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, strict=False)
    return model


def vgg16(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 16-layer model (configuration "D")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_.
    The required minimum input size of the model is 32x32.

    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
    """
    return _vgg('vgg16', 'D', False, pretrained, progress, **kwargs)

Functions

def vgg16(pretrained: bool = False, progress: bool = True, **kwargs: Any) ‑> torchvision.models.vgg.VGG

VGG 16-layer model (configuration "D") "Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>_. The required minimum input size of the model is 32x32.

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 vgg16(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 16-layer model (configuration "D")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_.
    The required minimum input size of the model is 32x32.

    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
    """
    return _vgg('vgg16', 'D', False, pretrained, progress, **kwargs)

Classes

class VGG (features: torch.nn.modules.module.Module, num_classes: int = 1000, init_weights: bool = True)

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

Initializes internal Module state, shared by both nn.Module and ScriptModule.

Expand source code

class VGG(nn.Module):

    def __init__(
        self,
        features: nn.Module,
        num_classes: int = 1000,
        init_weights: bool = True
    ) -> None:
        super(VGG, self).__init__()
        self.features = features
        self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
        self.classifier = nn.Sequential(
            nn.Linear(512 * 7 * 7, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x

    def _initialize_weights(self) -> None:
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)

Ancestors

torch.nn.modules.module.Module

Subclasses

earthvision.models.resisc45.vgg16.VGG16Resisc45

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: torch.Tensor) -> torch.Tensor:
    x = self.features(x)
    x = self.avgpool(x)
    x = torch.flatten(x, 1)
    x = self.classifier(x)
    return x