Rtx 2070 gpu

In this article, autoencoder and regression models were implemented in Python (version 3.7.13) using Keras (version 2.9.0), which is a high-level neural networks library (Chollet, 2022 ) and scikit-learn (version 1.0.2) which provides regression models and model evaluation tools (Lemaitre, 2021 ). All training and testing processes were performed using a computer with Intel i7 10870H CPU, 16GB Ram, and Nvidia RTX 2070 GPU.

To underscore that meaningful Bayesian inference does not require cluster computing or extensive computational resources, all computations were performed on a Windows MSI GS-66 laptop with an Intel i7 processor with an Nvidia RTX2070 GPU. Our inference programs are CPU-bound, not requiring any GPU resources. Computations can be performed on most modern CPUs, but are accelerated with more CPU threads and cores and parallelization on GPUs.

The model has been implemented in Tensorflow 1.13.1 and Keras 2.2.4 deep learning frameworks trained in a Linux PC with a Nvidia RTX 2070 GPU. From the comprehensive image dataset, the emotional categories of happiness, sadness and neutrality were selected, and the resulting dataset was divided into training and test datasets consisting of 20 689 and 750 images, respectively. The model was trained for 100 epochs with a batch size of 48 face images. Adam was used as a gradient descent optimization algorithm, and categorical cross entropy as a loss function [87 ]. Our model is initialized with a learning rate of 0.001, which is optimized by Adam during the learning procedure (see the electronic supplementary material, table S1 for the complete list of tensor dimensions and connections, and table S2 for model hyperparameters).