In this article, I want to share my experience using TensorRT, RetinaNet, based on an official (Nvidia) repository that will allow you to start using optimized models in production as soon as possible.
We need to mark up the dataset, train the RetinaNet / Unet network on Pytorch1.3+ on it, convert the received weights to ONNX, then convert them to the TensorRT engine run the whole thing in docker, on ARM (Jetson) architecture, thereby minimizing manual deployment surroundings. Our steps:
I saw how many articles wrote about Google Colab Activity, but now I’m going to make a device with the randomizer mouse activity. And of course, you can use this for any case when you need simulation activity.
What you need:
1. Raspberry pi pico
2. micro USB Adapter to any USB in your PC
3. PC with Thonny IDE (or any to coding for microcontroller)
4. 15–20min your time
I will not describe how to connect Pico and use IDE for the microcontroller; I think you have to know it or use Google search.
Hello, my friend and readers. Today I’m starting a new challenge for me in Robot manipulation based on stepper motors. I didn’t make the robot arm early, this is my first experience for it.
When I started this challenge I got a few issues:
I tried many days for R&D. It was youtube videos, Git repositories, online Forums, and engineering blogs. I observed and analyze maximum information for this specific environment.
It was my first adventure for programming robotics when I used my background in computer version (Deep Learning) and created a simple mini bot.
When I begin, I’d like to tell you a little about my BG projects. I started my journey when Nvidia announced an embedded GPU computer in March 2019. I used to use Nvidia CUDA and RT for my work and projects. I’ve Nvidia Jetson TX2 (many thanks — NVIDIA Inception Program for this), I created on this board many exciting projects. This device has been fundamentally boarding in my product — Safety on the crossroads.
Today I’m going to tell synthetics data and how it helps us in real world. I’ll not be telling about many types of synthetic data for ML (Machine Learning), I want to talk — synthetic data for Deep Learning, for learning on your own Neural Network.
Several months ago I had to do unique data for my first MVP. I’ve gotten many different problems with incorrect data:
I need to…
Remote work has many advantages and disadvantage.
Today I'm going to talk about how to configure local access between Raspberry Pi + Intel Movidius NCS and your Laptop. I'll be using MacBook pro 2017.
Organize local access to Raspberry + Movidius NCS = Quickly / Anywhere from your Laptop
- Raspberry has to give internet access
- ssh access to Raspberry pi from USB
Before you will go to your lovely cafeteria … you have to give ssh access to your Raspberry Pi
Here are 3 methods to enable SSH
Using the Desktop
Hi there my friend and future readers. I’m going to start writing about my current project and share interesting solutions.. Problems in my team (Building, Analytics, R&D, Engineering, Developing and so on..)
How can you make simple but amazing products based on Deep Learning? and - Why I do it? How implemented my projects to the real world and of course how it helped to real problem people. It'll be a series publication.
I'd like to tell you a few points for my experience… I don't know 🤷♂️ how it helps you .. but I think you have to know…
I’m just a Human who likes hardware/software engineer in AI, Deep Learning