darknet19#

holocron.models.darknet19(pretrained: bool = False, checkpoint: Checkpoint | None = None, progress: bool = True, **kwargs: Any) → DarknetV2[source]#

Darknet-19 from “YOLO9000: Better, Faster, Stronger”

Parameters:

pretrained (bool) – 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 (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.Darknet19_Checkpoint(value)[source]#

The model builder above accepts the following values as the checkpoint parameter. Darknet19_Checkpoint.DEFAULT is equivalent to Darknet19_Checkpoint.IMAGENETTE

Darknet19_Checkpoint.IMAGENETTE:

Also available as Darknet19_Checkpoint.DEFAULT.

dataset	imagenette
top1-accuracy	0.9386
top5-accuracy	0.9936
url	link
sha256	32fd3f9795865565
size	75.7MB
num_params	19.8M
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