Tag: data science
-
What is nn.Conv2d for in Pytorch?
nn.Conv2d is a class in the PyTorch deep learning framework that represents a 2-dimensional convolutional layer. Convolutional layers are a fundamental building block in Convolutional Neural Networks (CNNs), which are widely used for image processing, computer vision, and other tasks involving grid-like input data. The nn.Conv2d class is part of the torch.nn module, which provides […]
-
What computer for Machine Learning and MLOps
You are new to machine learning and you want to know what kind of computer, either a laptop or a PC you need for working in machine learning. The short answer is that you can buy or use any old banger laptop and you can learn machine learning by using free services like Google Colab. It […]
-
Imagen: Text-To-Image AI From Google
Google has taken AI-generated images to a new level with Imagen. Imagen is a new state-of-the-art text-to-image diffusion model capable of generating highly realistic images given text input. It uses a very powerful language model, T5–XXL a language model with 4.6 billion of parameters trained on a huge text-only dataset. This new model is not […]
-
How to resize an image with Tensorflow tf.image.resize()
When dealing with training data, you often need to resize images to a fixed size, according to the architecture of the machine learning model that you want to use. In Tensorflow we can use tf.image.resize() to resize images to different resolutions. The method controls the different algorithms that we can use for resizing. You can […]
-
Tensorflow not detecting GPU
If TensorFlow doesn’t detect your GPU, it will default to the CPU, which means when doing heavy training jobs, these will take a really long time to complete. This is most likely because the CUDA and CuDNN drivers are not being correctly detected in your system. I am assuming that you have already installed Tensorflow […]
-
Does CUDA 11.6 work with Tensorflow?
The short answer is No. The latest Tensorflow, which is currently Tensorflow 2.9, is not yet ready to work with CUDA 11.6. If you check the Tensorflow compatibility matrix below you will find that as of today the recommended CUDA version you should install is 11.2: Version Python version Compiler Build tools cuDNN CUDA tensorflow-2.9.0 […]
-
Installing Tensorflow 2.9 with GPU Support
You have come here because you want to install Tensorflow 2.9, and you want to get it right for the first time. Typically installing Tensorflow is hard work due to the number of dependencies. The good news is that since Tensorflow 2.5, the basic dependencies haven’t changed much, CUDA 11.2 and CuDNN 8.1 is still […]
-
How to setup Tensorflow on Ubuntu Linux with multiple GPUs using Docker
For this tutorial, I will be setting up the latest version of Tensorflow, currently 2.9 with GPU support on a workstation kindly provided by SabrePC with 4 x RTX 3080. For those curious, here is a clip of what this workstation looks like: Setting up Tensorflow typically requires a lot of hard work as you […]
-
Python Exercise for Beginners – Implementing One Hot Encoding
In today’s Python exercise we will create a one-hot encoding algorithm to convert categorical data to a numerical format. The reason why we need to do this is that machine learning algorithms only can deal with numbers, not strings. What is One Hot Encoding? One-hot encoding is a way of representing categorical information in binary […]
-
Reducing 90% in costs with Spot VMs for Machine Learning on Google Kubernetes Engine in GCP
When running big machine learning training jobs using neural networks, you need a GPU. And let’s be honest, GPUs are expensive and hard to get nowadays with the chip shortage! So it is unlikely that you will have plenty of spare GPUs lying around. This is why it makes sense to rent GPUs on the […]
