alexnet.py

from functools import partial
from typing import Any, Optional

import torch
import torch.nn as nn

from ..transforms._presets import ImageClassification
from ..utils import _log_api_usage_once
from ._api import WeightsEnum, Weights
from ._meta import _IMAGENET_CATEGORIES
from ._utils import handle_legacy_interface, _ovewrite_named_param


__all__ = ["AlexNet", "AlexNet_Weights", "alexnet"]


class AlexNet(nn.Module):
    def __init__(self, num_classes: int = 1000, dropout: float = 0.5) -> None:
        super().__init__()
        _log_api_usage_once(self)
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        self.classifier = nn.Sequential(
            nn.Dropout(p=dropout),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(p=dropout),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    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


class AlexNet_Weights(WeightsEnum):
    IMAGENET1K_V1 = Weights(
        url="https://download.pytorch.org/models/alexnet-owt-7be5be79.pth",
        transforms=partial(ImageClassification, crop_size=224),
        meta={
            "num_params": 61100840,
            "min_size": (63, 63),
            "categories": _IMAGENET_CATEGORIES,
            "recipe": "https://github.com/pytorch/vision/tree/main/references/classification#alexnet-and-vgg",
            "metrics": {
                "acc@1": 56.522,
                "acc@5": 79.066,
            },
        },
    )
    DEFAULT = IMAGENET1K_V1


@handle_legacy_interface(weights=("pretrained", AlexNet_Weights.IMAGENET1K_V1))
def alexnet(*, weights: Optional[AlexNet_Weights] = None, progress: bool = True, **kwargs: Any) -> AlexNet:
    r"""AlexNet model architecture from the
    `"One weird trick..." <https://arxiv.org/abs/1404.5997>`_ paper.
    The required minimum input size of the model is 63x63.

    Args:
        weights (AlexNet_Weights, optional): The pretrained weights for the model
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    weights = AlexNet_Weights.verify(weights)

    if weights is not None:
        _ovewrite_named_param(kwargs, "num_classes", len(weights.meta["categories"]))

    model = AlexNet(**kwargs)

    if weights is not None:
        model.load_state_dict(weights.get_state_dict(progress=progress))

    return model