Posted on Leave a comment

Baby Steps of Object Detection

Computer vision has been a hot topic in the past decade and this as well, with machines being able to identify objects as humans, with some errors as well. Since the pandemic has invaded the world, the world has chosen to stay still with minimal interactions to avoid the spread and infections. This has in fact affected us a lot, being a hardware startup. We had our product ready to be shipped when this hit, and with all revenues dried, combined with the lack of supply of components, we thought of stepping into the world of machine learning which required minimal hardware components.

Google Inc has come up with TensorFlow, a platform for neural network training. We, have initially used ImageAI on Python for our initial testing. We coded, and then found that the codes were running fine and the machine was learning after a few failed attempts. The most difficult part, we though, would be to find a proper hardware to test the models and to train them.

We opted to create a library of the things we wanted the model to identify and started with it. We tried training the model from scratch. But then, we later learnt that there are pre trained models which we could use and then train them for our data set. This turned out to be faster.

We came across Google CoLab while we had to run the models to train for hours. Google CoLab is a free tool which can run these training with specialized GPU and TPUs. We mounted our Google Drive for data set and to save the trained models.

This is our journey so far. Stay tuned, as we move ahead.

The tools that we have used are
https://imageai.readthedocs.io/
https://colab.research.google.com/

A snip from our training
Posted on Leave a comment

Happy New Year 2019 !

Dear Well-wishers,

Thank you for following us closely and wishing us success, though we were just starting up in the year 2018. The year has been not so eventful when it comes to the company and its product launches. We managed to register our company in India, in November 2018. And since then, we have been striving hard to bring in products for the people.

We thank you for following and encouraging us throughout the year, since our registration and beginning thereby. We hope that we would deliver products, in 2019, and we guarantee this as well. Your presence has kept our hopes alive, and we make a new years wish to grow up to the expectations.

We, the team, wish you all a Happy New Year 2019 ! May this year bring us all, the fortunes and luck that we wish for !

The Team,
RegalDream Technologies

Posted on Leave a comment

Project RDOne: 3D Drawing – New Version – Lessons of screw holes for 3D Print

A few days back, we had given a brief introduction on 3D printing that we had done for prototyping stage. Once the 3D Printing was done, and tested, we understood that there are a few difference between 3D Printed plastics when compared to the molded ones. For instance, we had a screwing mechanism to be used to screw in the PCB and cover to the main body. We were planning for a M2 x 6 mm screw to be used and thought of going with 1.9 mm hole so that the screw can create it’s own thread while being screwed.

Little did we know that while using 3D printing, there are chances that the material might flow in and out a bit, changing the dimensions. This means that our 1.9 mm hole in drawing will in actual model would be somewhere much less than 1.9 mm. Our 3D printing friend, Magesh, gave us a suggestion of going with +0.1 mm for the dimension of hole.

If the screw hole is more, you can always use ABS glue to reduce the size of the hole. ABS glue, as I read, is made by mixing ABS Plastic in acetone. We will try this method, and keep you updated !

Follow us and stay updated on our progress and life at RegalDream Technologies !