DarkNetV2¶

The DarkNetV2 model is based on the "YOLO9000: Better, Faster, Stronger" paper.

Architecture overview¶

This paper improves its version version by adding more recent gradient flow facilitators.

The key takeaways from the paper are the following:

adds batch normalization layers compared to DarkNetV1

Model builders¶

The following model builders can be used to instantiate a DarknetV2 model, with or without pre-trained weights. All the model builders internally rely on the DarknetV2 base class.

DarknetV2 ¶

DarknetV2(layout: list[tuple[int, int]], num_classes: int = 10, in_channels: int = 3, stem_channels: int = 32, act_layer: Module | None = None, norm_layer: Callable[[int], Module] | None = None, drop_layer: Callable[..., Module] | None = None, conv_layer: Callable[..., Module] | None = None)

Bases: Sequential

Source code in holocron/models/classification/darknetv2.py

def __init__(
    self,
    layout: list[tuple[int, int]],
    num_classes: int = 10,
    in_channels: int = 3,
    stem_channels: int = 32,
    act_layer: nn.Module | None = None,
    norm_layer: Callable[[int], nn.Module] | None = None,
    drop_layer: Callable[..., nn.Module] | None = None,
    conv_layer: Callable[..., nn.Module] | None = None,
) -> None:
    super().__init__(
        OrderedDict([
            (
                "features",
                DarknetBodyV2(
                    layout, in_channels, stem_channels, False, act_layer, norm_layer, drop_layer, conv_layer
                ),
            ),
            ("classifier", nn.Conv2d(layout[-1][0], num_classes, 1)),
            ("pool", GlobalAvgPool2d(flatten=True)),
        ])
    )

    init_module(self, "leaky_relu")

darknet19 ¶

darknet19(pretrained: bool = False, checkpoint: Checkpoint | None = None, progress: bool = True, **kwargs: Any) -> DarknetV2

Darknet-19 from "YOLO9000: Better, Faster, Stronger"

PARAMETER	DESCRIPTION
`pretrained`	If True, returns a model pre-trained on ImageNette TYPE: `bool` DEFAULT: `False`
`checkpoint`	If specified, the model's parameters will be set to the checkpoint's values TYPE: `Checkpoint \| None` DEFAULT: `None`
`progress`	If True, displays a progress bar of the download to stderr TYPE: `bool` DEFAULT: `True`
`kwargs`	keyword args of `DarknetV2` TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`DarknetV2`	classification model

Darknet19_Checkpoint ¶

Bases: Enum

IMAGENETTE `class-attribute` `instance-attribute` ¶

IMAGENETTE = _checkpoint(arch='darknet19', url='https://github.com/frgfm/Holocron/releases/download/v0.2.1/darknet19_224-32fd3f97.pth', acc1=0.9386, acc5=0.9936, sha256='32fd3f979586556554652d650c44a59747c7762d81140cadbcd795179a3877ec', size=79387724, num_params=19827626, commit='6e32c5b578711a2ef3731a8f8c61760ed9f03e58', train_args='./imagenette2-320/ --arch darknet19 --batch-size 64 --mixup-alpha 0.2 --amp --device 0 --epochs 100 --lr 1e-3 --label-smoothing 0.1 --random-erase 0.1 --train-crop-size 176 --val-resize-size 232 --opt adamw --weight-decay 5e-2')

DEFAULT `class-attribute` `instance-attribute` ¶

DEFAULT = IMAGENETTE