Implement EfficientNet backbone

Nobody has claimed this yet.

This recently came out

https://arxiv.org/abs/1905.11946

> EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

with incredible practical implications: we can either get a much better backbone than our current resnet50 for the same computational budget or get a highly computationally efficient backbone and roughly keep the resnet50's prediction performance.

Here's why we should look into this
- it's simple and easy to implement
- it provides huge practical engineering gains we care about (size, runtime)
- the accuracy is same or higher (depending on EfficientNet model)

Check out the paper's table 2 (below) for comparisons; we are currently using a resnet50.

I highlighted
- the resnet50 we are currently using
- the EfficientNet-B0 which reaches roughly the same accuracy as resnet50 but is x4.9 smaller and requires x11 less flops
- the EfficientNet-B4 which is a bit smaller than the resnet50, requires roughly the same amount of flops than the resnet50, but reaches a much higher accuracy



Read the linked EfficientNet paper, especially Table 2, and inspect where the current ResNet50 backbone is configured. Define the EfficientNet-B0/B4 scope and how size, runtime, and prediction performance will be compared; the issue provides no file, test, or acceptance criterion, so completion needs those details established.

Written by the indexing model from the issue text.