cspdarknet53_mish#

holocron.models.cspdarknet53_mish(pretrained: bool = False, checkpoint: Checkpoint | None = None, progress: bool = True, **kwargs: Any) → DarknetV4[source]#

Modified version of CSP-Darknet-53 from “CSPNet: A New Backbone that can Enhance Learning Capability of CNN” with Mish as activation layer and DropBlock as regularization layer.

Parameters:

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

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

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

  • kwargs – keyword args of _darknet

Returns:

classification model

Return type:

torch.nn.Module

class holocron.models.CSPDarknet53_Mish_Checkpoint(value)[source]#

The model builder above accepts the following values as the checkpoint parameter. CSPDarknet53_Mish_Checkpoint.DEFAULT is equivalent to CSPDarknet53_Mish_Checkpoint.IMAGENETTE

CSPDarknet53_Mish_Checkpoint.IMAGENETTE:

Also available as CSPDarknet53_Mish_Checkpoint.DEFAULT.

dataset

imagenette

top1-accuracy

0.9465

top5-accuracy

0.9969

url

link

sha256

1b660b3cb1441951

size

101.8MB

num_params

26.6M

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

6e32c5b