I'm running PixInsight 1.8.8-12 on Windows 11, with an AMD Ryzen 7 5800X CPU and NVIDIA GeForce RTX 3070 GPU. Your mileage will vary depending on your hardware configuration, as well as the image that you run through StarNet. By no means is this an exhaustive test, nor do I guarantee that everyone else will see similar results. I wanted to test how well DirectML works compared to CUDA and stock CPU, so I ran a very short test. A PDF version of this tutorial will be made available shortly. It is meant to be used with the standalone StarNet++ module written by nekitmm, which can be found on SourceForge. This tutorial is written for StarNet V1, and PixInsight 1.8.8-12. When TF2.x support is released for DirectML, I'll be sure to update this article promptly! This means that the latest version StarNet's checkpoint files are incompatible with the DirectML version of libtensorflow.dll. Unfortunately, Microsoft's latest release of DirectML (1.15.5) is only compatible with Tensorflow 1.x, while Starnet V2 uses TF2.x. Although all modern NVIDIA GPU's support DirectX 12, CUDA is still the preferred method, as it works natively with both TF and the GPU. However, Windows devices running any graphics device - including integrated graphics - that support Microsoft DirectX 12 can take advantage of Microsoft DirectML to hardware-accelerate Tensorflow processes. Classically, only people with NVIDIA GPU's were able to accelerate StarNet, since TensorFlow only officially supports CUDA.
If you've used StarNet before, you know long it takes sometimes to process a single image.
0 kommentar(er)
