ResNet / ResNeXt / SE-ResNeXt / SE-Net This class implements all variants of ResNet, ResNeXt, SE-ResNeXt, and SENet that * have > 1 stride

Selectable global pooling layer with dynamic input kernel size

Computes and stores the average and current value

Randomly selects a rectangle region in an image and erases its pixels. 'Random Erasing Data Augmentation' by Zhong et al. See https:/

Sampler that restricts data loading to a subset of the dataset. It is especially useful in conjunction with :class:`torch.nn.parallel.Distribu

r"""Densenet-BC model class, based on `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>` Args: growt

Build Trunk Blocks This ended up being somewhat of a cross between https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mna

Inverted residual block w/ CondConv routing

DropBlock. See https://arxiv.org/pdf/1810.12890.pdf

Residual block with expansion convolution followed by pointwise-linear w/ stride

NLL loss with label smoothing.

Resize the given PIL Image randomly. Args: scale: range of size of the origin size cropped interpolation: Default: PIL

r"""Implements AdamW algorithm. The original Adam algorithm was proposed in `Adam: A Method for Stochastic Optimization`_. The AdamW variant

AugMix Transform Adapted and improved from impl here: https://github.com/google-research/augmix/blob/master/imagenet.py From paper: 'AugMix:

Dataset wrapper to perform AugMix or other clean/augmentation mixes

Original CBAM channel attention module, currently avg + max pool variant only.

Conditionally Parameterized Convolution Inspired by: https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/condconv/condconv

Tensorflow like 'SAME' convolution wrapper for 2D convolutions

Cosine decay with restarts. This is described in the paper https://arxiv.org/abs/1608.03983. Inspiration from https://github.com/all

DepthwiseSeparable block Used for DS convs in MobileNet-V1 and in the place of IR blocks that have no expansion (factor of 1.0). This is an a

Inverted residual block w/ optional SE and CondConv routing

DepthwiseSeparable block Used for DS convs in MobileNet-V1 and in the place of IR blocks that have no expansion (factor of 1.0). This is an a

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Build Trunk Blocks This ended up being somewhat of a cross between https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mna

Inverted residual block w/ optional SE and CondConv routing

Jensen-Shannon Divergence + Cross-Entropy Loss Based on impl here: https://github.com/google-research/augmix/blob/master/imagenet.py From pa

An experimental 'lightweight' that sums avg + max pool first

An experimental 'lightweight' variant that sums avg_pool and max_pool results.

Mixed Grouped Convolution Based on MDConv and GroupedConv in MixNet impl: https://github.com/tensorflow/tpu/blob/master/models/official/mn

Model Exponential Moving Average Keep a moving average of everything in the model state_dict (parameters and buffers). This is intended to a