CondConv initializer function.

Create a model Args: model_name (str): name of model to instantiate pretrained (bool): load pretrained ImageNet-1k weights if tru

Create a model Args: model_name (str): name of model to instantiate pretrained (bool): load pretrained ImageNet-1k weights if tru

Create a model Args: model_name (str): name of model to instantiate pretrained (bool): load pretrained ImageNet-1k weights if tru

r"""Densenet-121 model from `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`

r"""Densenet-201 model from `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`

r"""Densenet-169 model from `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`

r"""Densenet-201 model from `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`

Constructs an ECA-ResNet-18 model.

Constructs an ECA-ResNet-50 model.

Constructs an ECA-ResNeXt-26-TN model. This is technically a 28 layer ResNet, like a 'D' bag-of-tricks model but with tiered 24, 32, 64 channels

EfficientNet-B0

EfficientNet-B1

EfficientNet-B2

EfficientNet-B2 @ 288x288 w/ 1.0 test crop

EfficientNet-B3

EfficientNet-B3 @ 320x320 w/ 1.0 test crop-pct

EfficientNet-B4

EfficientNet-B5

EfficientNet-B6

EfficientNet-B7

EfficientNet-B7

EfficientNet-B8

EfficientNet-CondConv-B0 w/ 8 Experts

EfficientNet-CondConv-B0 w/ 8 Experts

EfficientNet-CondConv-B1 w/ 8 Experts

EfficientNet-B7

EfficientNet-B7

EfficientNet-Edge-Large.

EfficientNet-Edge-Medium.

EfficientNet-Edge Small.

EfficientNet-L2.

r""" Ensemble Adversarially trained InceptionResnetV2 model architecture As per https://arxiv.org/abs/1705.07204 and https://github.com/tensor

A fast collation function optimized for uint8 images (np array or torch) and int64 targets (labels)

A fast collation function optimized for uint8 images (np array or torch) and int64 targets (labels)

FBNet-C

Feature Channel Shortcut Returns feature channel count for each output index if idx == None. If idx is an integer, will return featur

Feature Channel Shortcut Returns feature channel count for each output index if idx == None. If idx is an integer, will return featur