Getting Started with TensorFlow and Keras - Maker.io | Digi-Key Electronics
ฝัง
- เผยแพร่เมื่อ 10 ก.ย. 2024
- In this tutorial, we show you how to configure TensorFlow with Keras on a computer and build a simple linear regression model. If you have access to a modern NVIDIA graphics card (GPU), you can enable tensorflow-gpu to take advantage of the parallel processing afforded by CUDA.
The field of Artificial Intelligence (AI) has been around for quite some time. As we move to build an understanding and use cases for Edge AI, we first need to understand some of the popular frameworks for building machine learning models on personal computers (and servers!).
These models can then be deployed to edge devices, such as single-board computers (like the Raspberry Pi) and microcontrollers. To learn more about Edge AI, see this article: www.digikey.co...
Project Link:
www.digikey.co...
Related Videos:
Intro to TensorFlow Lite Part 1: Wake Word Feature Extraction
• Intro to TensorFlow Li...
Intro to TensorFlow Lite Part 2: Speech Recognition Model Training
• Intro to TensorFlow Li...
Intro to TensorFlow Lite Part 3: Speech Recognition on Raspberry Pi
• Intro to TensorFlow Li...
Related Articles:
www.digikey.co...
Maker.io - www.digikey.co...
Digi-Key’s Blog - TheCircuit www.digikey.co...
Connect with Digi-Key on Facebook / digikey.electronics
And follow us on Twitter / digikey
The easiest way I've found to install TensorFlow GPU on Windows is to install Anaconda and then in a terminal: conda create --name tf_gpu tensorflow-gpu . This has the benefit of including CUDA, cuDNN and the other software you need.
Good to know there's an easier method. Thanks!
very good if not already excellent, love the way you make things simple..!! thank you
Excellent !
For Windows, install Visual Studio first then CUDA after that otherwise, you may get a "imported project not found" error when you try to build CUDA Visual Studio projects.
I only wish I could compile as fast as him!
If you install Anaconda now, you have to make sure to create an env with a compatible python version. For me this was "conda create -n tensorflow python=3.8"