More optimizer work

Optimizers and more

Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak.
* Add some of the trendy new optimizers. Decent results but not clearly better than the standards.
* Can create a None scheduler for constant LR
* ResNet defaults to zero_init of last BN in residual
* add resnet50d config

MixNet-XL

Add support to split random erasing blocks into randomly selected number with --recount arg. Fix random selection of aspect ratios.

Port Gluon Aligned Xception models

Update helpers.py

Fixing out of memory error by loading the checkpoint onto the CPU.

Add new auto-augmentation Tensorflow EfficientNet weights, incl B6 and B7 models. Validation scores still pending but looking good.

Add native PyTorch weights for MixNet-Medium with no SAME padding necessary. Remove unused block of code.

Add MixNet (https://arxiv.org/abs/1907.09595) with pretrained weights converted from Tensorflow impl
* refactor 'same' convolution and add helper to use MixedConv2d when needed
* improve performance of 'same' padding for cases that can be handled statically
* add support for extra exp, pw, and dw kernel specs with grouping support to decoder/string defs for MixNet
* shuffle some args for a bit more consistency, a little less clutter overall in gen_efficientnet.py

* remove folded_bn support and corresponding untrainable tflite ported weights
* combine bn args into dict
* add inplace support to activations and use where possible for reduced mem on large models

Resnet refactoring