Generate bbox and apply lambda correction.

Parameters ---------- block (nn.Module): Bottleneck class. - For SENet154: SEBottleneck - For SE-ResN

With 50% prob, negate the value

Creates an EfficientNet-V2 base model Ref impl: https://github.com/google/automl/tree/master/efficientnetv2 Paper: `EfficientNetV2: Smaller

Creates an EfficientNet-V2 Large model Ref impl: https://github.com/google/automl/tree/master/efficientnetv2 Paper: `EfficientNetV2: Smaller

Creates an EfficientNet-V2 Medium model Ref impl: https://github.com/google/automl/tree/master/efficientnetv2 Paper: `EfficientNetV2: Smalle

Creates a mnasnet-a1 model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet Paper: https://arxiv.org/pdf/1807

Creates a mnasnet-b1 model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet Paper: https://arxiv.org/pdf/1807

Generate MobileNet-V2 network Ref impl: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py Paper:

return info dicts for specified keys (or all if None) at specified indices (or out_indices if None)

Insert CLS token.

VovNet (v2)

Constructs a GhostNet model

FBNetV3 Paper: `FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining` - https://arxiv.org/abs/2006.02049 FIXME untes

Gets all parameters in all param_groups with gradients

Feature map interpolation.

See http://www.codinghorror.com/blog/archives/001018.html

Override model level attn/self-attn/block kwargs w/ block level NOTE: kwargs are NOT merged across levels, block_kwargs will fully replace model

Feature map up-sampling.