We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming. The torchbearer library provides a high level metric and callback API that can be used for a wide range of applications. We also include a series of built in callbacks that can be used for: model persistence, learning rate decay, logging, data visualization and more. The extensive documentation includes an example library for deep learning and dynamic programming problems and can be found at http://torchbearer.readthedocs.io.

As the TechSparks countdown begins, we list the top Bengaluru startups that have grabbed the spotlight due to the work they do and the growth they are projecting. Bengaluru has always been referred to as India's Silicon Valley. This is not just in terms of the number of startups that have mushroomed in the city, but also keeping in mind the funding pumped into the Bengaluru startup ecosystem. According to YourStory data, between 2016 and 2017 (YTD), the total amount of funding raised by Bengaluru startups was a whopping $6.6 billion. As many as 460 startups have made Bengaluru their home in the past two years, be it e-commerce giant Flipkart, cab aggregator Ola or Practo, one of the top funded healthcare startups in India.