Category: AI
-
Visualizing a neural network in 3D with Python, Blender and Tensorflow
I have started recently a new project in which I am trying to visualize a neural network in 3D with Python, Blender and Tensorflow. This is a very interesting challenge and a great way to learn things that I didn’t know I needed to know. For example how to get access to the different layers […]
-
Convert a photo from 2D to 3D model with color with PIFu
This is a short tutorial on how you can convert and train Pifu to convert a 2D photo to a 3D Model with color. Pifu is the predecessor to PIFuHD. PIFU in theory can be trained to create 3D Models for any type of object, not just humans, but of course, you will need to […]
-
PHORHUM: From a 2D photo to 3D animated model by Google
Google has released a paper on a new state-of-the-art machine learning model, called PHORHUM, that is able to create a 3D model from a single 2D photo, with texture disentangled from the lighting source in the photo. There is only one bad news. Google hasn’t yet released source code or a demo for anyone to […]
-
Creating my own image dataset for Tensorflow with CVAT
So, I have created a Raspberry PI wildlife camera, but it has a big cat issue! Or shall I say, a big dog issue?! The Tensorflow model I am using mistakes everything for a dog. A fox, a cat, a person, and some sunshine can all be mistaken for a dog. So I have to do […]
-
From a 2D Photo to a 3D Model with Nvidia Ganverse3D with Nvidia Omniverse Create
Remember that a few months ago I talked about a new ground-breaking application, yet to be released, from Nvidia Research Labs, called GanVerse3D, capable of rendering 3D models with texture from 2D photos? Not only that, GanVerse3D was also supposed to be capable of animating the 3D model at a click of a button. Yes, […]
-
How to turn 2D photos into a 3D model using Nvidia Kaolin and PyTorch – A 3D Deep Learning Tutorial
If you have read my last article on GANverse3D, then you will probably have heard about the DIB-R paper, which I mentioned a few times. This was a key paper for 3D Deep Learning from 2019. The DIB-R paper introduced an improved differential renderer as a tool to solve one of the most fashionable problems […]
-
How to install Tensorflow 2.5 with CUDA 11.2 and CuDNN 8.1 for Windows 10
In this article, I am going to show you how you can install Tensorflow 2.5, CUDA 11.2.1, and CuDNN 8.1, for Windows 10, with full support for an Nvidia GPU RTX 30 series card. Since CUDA is backward compatible it should also work for RTX 20 series cards or older. But before I install CUDA, […]
-
Nvidia Resizable BAR for all RTX 30 Series GPUs and what will it mean for Deep Learning
After Nvidia‘s release of “Resizable BAR” memory support for the RTX 3060 at launch, Nvidia has now extended this feature to all RTX-30 series cards.This means that for a select number of games, it is possible to see a performance boost when Resizable BAR is enabled. But is Resizable BAR support only enabled for gaming […]
-
Is the new Nvidia RTX 3060 good for beginners in Deep Learning, and is the crypto mining ban going to help?
Based on pure specs alone, the new Geforce RTX 3060 is a brilliant budget proposition for anyone looking to get into Deep Learning. It has plenty of CUDA cores(3584) and 12GB of GDDR6 memory. With the added benefit that you can also use it for gaming too if that’s something you fancy. And finally, I […]
-
Tensorflow Object Detection API – Custom Image Classification — Can I detect if a painting is a nativity painting?
Can I teach an AI model using Tensorflow Object Detection API, how to identify the theme of a painting? The only way to find out is by trying! And I think you might be surprised by the outcome of this experiment. But, I am going to narrow down my problem. I want to identify if […]
