repvgg_b2#

holocron.models.repvgg_b2(pretrained: bool = False, checkpoint: Checkpoint | None = None, progress: bool = True, **kwargs: Any) → RepVGG[source]#

RepVGG-B2 from “RepVGG: Making VGG-style ConvNets Great Again”

Parameters:

  • pretrained – If True, returns a model pre-trained on ImageNette

  • checkpoint – If specified, the model’s parameters will be set to the checkpoint’s values

  • progress – If True, displays a progress bar of the download to stderr

  • kwargs – keyword args of _repvgg

Returns:

classification model

Return type:

torch.nn.Module

class holocron.models.RepVGG_B2_Checkpoint(value)[source]#

The model builder above accepts the following values as the checkpoint parameter. RepVGG_B2_Checkpoint.DEFAULT is equivalent to RepVGG_B2_Checkpoint.IMAGENETTE

RepVGG_B2_Checkpoint.IMAGENETTE:

Also available as RepVGG_B2_Checkpoint.DEFAULT.

dataset

imagenette

top1-accuracy

0.9414

top5-accuracy

0.9957

url

link

sha256

dc810d889e8533f3

size

601.2MB

num_params

157.5M

categories

tench, English springer, cassette player, … (7 omitted)

input_shape

(3, 224, 224)

mean

(0.485, 0.456, 0.406)

std

(0.229, 0.224, 0.225)

interpolation

InterpolationMode.BILINEAR

commit

d4a5999