ResNeXt¶

The ResNeXt model is based on the "Aggregated Residual Transformations for Deep Neural Networks" paper.

Architecture overview¶

This paper improves the ResNet architecture by increasing the width of bottleneck blocks

The key takeaways from the paper are the following:

increases the number of channels in bottlenecks
switches to group convolutions to balance the number of operations

Model builders¶

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

resnext50_32x4d ¶

resnext50_32x4d(pretrained: bool = False, checkpoint: Checkpoint | None = None, progress: bool = True, **kwargs: Any) -> ResNet

ResNeXt-50 from "Aggregated Residual Transformations for Deep Neural Networks"

PARAMETER	DESCRIPTION
`pretrained`	If True, returns a model pre-trained on ImageNet TYPE: `bool` DEFAULT: `False`
`checkpoint`	If specified, load that checkpoint on the model 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 `ResNet` TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`ResNet`	classification model

ResNeXt50_32x4d_Checkpoint ¶

Bases: Enum

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

IMAGENETTE = _checkpoint(arch='resnext50_32x4d', url='https://github.com/frgfm/Holocron/releases/download/v0.2.1/resnext50_32x4d_224-5832c4ce.pth', acc1=0.9455, acc5=0.9949, sha256='5832c4ce33522a9eb7a8b5abe31cf30621721a92d4f99b4b332a007d81d071fe', size=92332638, num_params=23000394, commit='6e32c5b578711a2ef3731a8f8c61760ed9f03e58', train_args='./imagenette2-320/ --arch resnext50_32x4d --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

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

def resnext50_32x4d(
    pretrained: bool = False,
    checkpoint: Checkpoint | None = None,
    progress: bool = True,
    **kwargs: Any,
) -> ResNet:
    """ResNeXt-50 from
    ["Aggregated Residual Transformations for Deep Neural Networks"](https://arxiv.org/pdf/1611.05431.pdf)

    Args:
        pretrained: If True, returns a model pre-trained on ImageNet
        checkpoint: If specified, load that checkpoint on the model
        progress: If True, displays a progress bar of the download to stderr
        kwargs: keyword args of [`ResNet`][holocron.models.ResNet]

    Returns:
        classification model

    ::: holocron.models.ResNeXt50_32x4d_Checkpoint
        options:
            heading_level: 4
            show_if_no_docstring: true
    """
    kwargs["width_per_group"] = 4
    block_args = {"groups": 32}
    return _resnet(
        checkpoint,
        progress,
        Bottleneck,
        [3, 4, 6, 3],
        [64, 128, 256, 512],
        block_args=block_args,
        **kwargs,
    )

resnext101_32x8d ¶

resnext101_32x8d(pretrained: bool = False, checkpoint: Checkpoint | None = None, progress: bool = True, **kwargs: Any) -> ResNet

ResNeXt-101 from "Aggregated Residual Transformations for Deep Neural Networks"

PARAMETER	DESCRIPTION
`pretrained`	If True, returns a model pre-trained on ImageNet TYPE: `bool` DEFAULT: `False`
`checkpoint`	If specified, load that checkpoint on the model 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 `ResNet` TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`ResNet`	classification model