CONVOLUTIONAL PROPERTIES OF A NEURAL NETWORK BASED ON AUTOENCODERS
DOI:
https://doi.org/10.31649/1999-9941-2021-52-3-77-85Keywords:
data set, training, neural network, autoencoder, convolutionAbstract
The convolutional properties of the autoencoding neural network for the object detection problem in the image are considered. Data sets in the form of two-dimensional images with three color channels were generated for training and testing. The images are generated based on a three-dimensional scene consisting of objects such as spheres, cubes, cylinders and “monkey” models. The time of network training on the data with different configurations and the result at the output of the neural network were estimated.
References
L. Yasenko, Y. Klyatchenko and O. Tarasenko-Klyatchenko, «Image noise reduction by denoising autoencoder», 2020 IEEE 11th International Conference on Dependable Systems, Services and Technologies (DESSERT), Kyiv, Ukraine, 2020, pp. 351-355, doi:10.1109/DESSERT50317.2020. 9125027.
Michael Seul, Lawrence O'Gorman, Michael J. Sammon, Practical Algorithms for Image Analysis. [Online]. Available: https://books.google.com.ua/books?id=5xcIErZZIN8C&printsec=frontcover&dq =Practical+Algorithms+for+Image+Analysis&hl=uk&sa=X&redir_esc=y#v=onepage&q=Practical%20Algorithms%20for%20Image%20Analysis&f=false.
R. Gonzalez, R. Woods. Digital image processing. Moscow: Technosphere. 2005, 1072p. [in Rusian].
A Comprehensive Guide to Convolutional Neural Networks − the ELI5 way. Sumit Saha. [Online]. Available: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53.
Convolutional Neural Network (CNN). [Online]. Available: https://developer.nvidia.com/discover/convolutional-neural-network.
Conv2d. [Online]. Available: https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html.
ConvTranspose2d. [Online]. Available: https://pytorch.org/docs/stable/generated/torch.nn.ConvTranspose2d.html#torch.nn.ConvTranspose2d.
Downloads
-
PDF (Українська)
Downloads: 130
