On building PyTorch libs in Docker

Recently I've been building containerized apps written in Caffe2/PyTorch. One of them had a dependency on a third-party API with some custom PyTorch modules built via torch.utils.ffi. This is a three-step process:

1. nvcc compiles the CUDA code and builds a shared object.
2. PyTorch utils create an FFI

Feature-matching Generative Adversarial Networks

## Motivation

Training a GAN is tricky, unstable process, especially when the goal is to get the generator to produce diverse images from the target distribution. In practice, in deep convolutional GANs generators overfit to their respective discriminators, which gives lots of repetitive generated images.

Generative Adversarial Networks, Source: ResearchGate

Feature

Evaluating scoring models from business perspective

## Scoring model

Many businesses use binary classification in their operations, typically employing it for differentiating "good events" from "bad events". Generally these algorithms first assign some number between 0 and 1 (score) to an event, and then make a decision how to intepret this score according