rexnet1_5x#

holocron.models.rexnet1_5x(pretrained: bool = False, checkpoint: Checkpoint | None = None, progress: bool = True, **kwargs: Any) → ReXNet[source]#

ReXNet-1.5x from “ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network”

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 _rexnet

Returns:

classification model

Return type:

torch.nn.Module

class holocron.models.ReXNet1_5x_Checkpoint(value)[source]#

The model builder above accepts the following values as the checkpoint parameter. ReXNet1_5x_Checkpoint.DEFAULT is equivalent to ReXNet1_5x_Checkpoint.IMAGENET1K

ReXNet1_5x_Checkpoint.IMAGENET1K:

Also available as ReXNet1_5x_Checkpoint.DEFAULT.

dataset	imagenet-1k
top1-accuracy	0.8031
top5-accuracy	0.9517
url	link
sha256	c42a16ac73470d64
size	13.7MB
num_params	9.7M
categories	tench, goldfish, great white shark, … (997 omitted)
input_shape	(3, 224, 224)
mean	(0.485, 0.456, 0.406)
std	(0.229, 0.224, 0.225)
interpolation	InterpolationMode.BILINEAR
commit	None

ReXNet1_5x_Checkpoint.IMAGENETTE:

dataset	imagenette
top1-accuracy	0.9447
top5-accuracy	0.9962
url	link
sha256	4b9d7a5901da6c2b
size	30.2MB
num_params	7.8M
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	d4a5999