20.500.12556/DKUM-72053 Izgubno stiskanje slik z variacijskim avtokodirnikom Lossy image compression using variational autoencoder V magistrskem delu preučujemo izgubno stiskanje slik z uporabo variacijskega avtokodirnika. Implementirali smo njegovo povratno različico, imenovano konvolucijski DRAW, ki v vlogi kodirnika in dekodirnika uporablja nevronsko mrežo LSTM. Za implementacijo smo uporabili jezik Python in knjižnico PyTorch. Delovanje algoritma smo testirali na podatkovni zbirki CIFAR-10 ter rezultate primerjali z metodo JPEG. Ugotovili smo, da so rezultati primerljivi v smislu kakovosti rekonstrukcije. In this thesis we study lossy image compression using variational autoencoder. We implemented its recurrent variant called convolutional DRAW, which uses a LSTM neural network in the role of the encoder and the decoder. The implementation was done in Python using the PyTorch library. The performance was tested the CIFAR-10 dataset and the results compared to the JPEG compression method. We determined that the results are comparable in reconstruction quality. stiskanje slik nevronske mreže variacijski avtokodirnik konvolucijski DRAW image compression neural networks variational autoencoder convolutional DRAW true true false Ž. Leber Slovenski jezik Angleški jezik Magistrsko delo/naloga 2018-09-09 14:21:55 2018-10-25 09:18:00 2022-08-01 21:54:51 2019-07-11 19:04:26 2018 0 [Maribor 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.627:004.932(043.2) 21878294 URN:SI:UM:DK:W61USHGO MAG_Leber_Ziga_2018.pdf MAG_Leber_Ziga_2018.pdf 1 FE6F272281694AD7A2DE61F2776E5A12 066a4b6568ed44b8e695e14557556431cbe6869715cca6c2a90695277714ae55 47d3aa4f-7c10-11eb-bb7a-00155d0001ca 20.500.12556/dkum/05d098a9-3650-4633-8626-8b8c08137708 https://dk.um.si/Dokument.php?lang=slv&id=128991 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0