Disclaimer: This post is not about how to create dotfiles and what should be included in those dotfiles. I am expecting readers of this post to have their own basic/well-defined dotfiles. This post will be mainly focusing on how to manage your existing dotfiles like a pro!
Let’s start with a scenario where I have faced endless problems when I installed a new os on my desktop or got a new system from the office.
Cloud Dataflow is an excellent tool for moving data within GCP and several blog post has been dedicated on how to perform ETL using dataflow and apache beam. Out of those several articles very less are focused on how to move data from bigquery to cloud storage in a specific format.
For the problem, I was working on. We had an internal ML framework which only reads data in a parquet format. …
Ever since Google Cloud released Cloud Function (BETA), there has been lots of excitement in the community. Google Cloud functions is an event-driven serverless compute platform which abstracts major configurations form developers like auto-scaling, on-demand execution and no server provisioning. This helps a developer to focus more on the development of service. And that’s the reason where we are also excited.
Before Moving to serverless applications I will briefly explain what is Google Cloud Functions.
Don’t worry mate my car knows how to follow a lane!
This post is an extension of what I wrote in my second blog on Lane Detection. This write-up will cover more on advance computer vision for lane detection.
This was the fourth project that I completed for my Udacity Self-Driving Cars Nanodegree program. My initial assumption for a reader here is that you know a little bit about the basics of a curved line (2nd order equation) and basics of computer vision.
For self-driving cars and autonomous robots, identifying lanes becomes a crucial part of development for smoother operation…
You sit tight mate, I will drive for you!
Let me first quote what is Behaviour Cloning?
Behavioural cloning is a method by which human sub-cognitive skills can be captured and reproduced in a computer program. As the human subject performs the skill, his or her actions are recorded along with the situation that gave rise to the action. A log of these records is used as input to a learning program. The learning program outputs a set of rules that reproduce the skilled behaviour. This method can be used to construct automatic control systems for complex tasks for which…
Can’t you please put your lane detection mode on!
This was the first project I completed for my Udacity Self-Driving Engineer Nanodegree program.
In any of the self-driving car system “Lane Detection” is one of the basic requirement to implement. This whole post is about step by step implementation for lane detection and this is implemented in python using OpenCV library. My initial assumption reader here is that you know a little bit about line equation and basics of computer vision.
Let's take an example image and try to build a pipeline for identifying lane lines on the road.
Yes, officer, My car saw the speed limit sign. I just overrode the accelerator pedal.
Recognising traffic signs is one of the essential parts of the race to ultimate Self-Driving Car System and Deep Learning plays a big role in the development this system. This post is all about step by step development of classifier for German Traffic Sign which is also a part of my project for Udacity Self-Driving Engineer Nanodegree.
My initial assumption for the readers is that a reader knows a little bit about the neural network and basic Image processing. This whole classifier is built in Python…
Machine Learning Engineer. Self-driving car Engg enthusiast and Dota 2 player.