|
|
Generating Faces with Conditional Generative Adversarial Networks
Venkrbec, Tomáš ; Hradiš, Michal (referee) ; Kolář, Martin (advisor)
The main goal of this thesis is to implement and compare models based on various architectures of conditional generative adversarial networks. Their main purpose is to conditionally generate realistic looking human faces with selected features. Results from models using DCGAN, WGAN-GP and ProGAN architectures were compared. Models were implemented using Tensorflow library and were trained on Flickr-Faces-HQ dataset. Across all used architectures, I managed to train models capable of generating realistic human faces, with an option to select age and gender.
|
|
|
GAN Generated Data for CNN Age Estimation
Venkrbec, Tomáš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The goal of this thesis is to implement one of the state-of-the-art methods of generative adversarial networks and to propose its extension to conditional generation. This has been used to generate photorealistic images of human faces with specified characteristics such as age and gender. For this purpose, a highly diverse dataset of over 230,000 samples was created by merging and cleaning existing annotated face datasets. All ages, genders and different ethnic groups are well represented in it. StyleGAN2 generator trained on this dataset achieved a FID of 7.14. The synthetic data ratio was then experimented with during age classifier training. For the test subset of the dataset, the addition of synthetic data achieved a reduction in the mean absolute error from 3.499 years to 3.294 years. For the independent test dataset, a reduction in mean error from 4.012 years to 3.875 years was achieved.
|
|
|
Generating Faces with Conditional Generative Adversarial Networks
Venkrbec, Tomáš ; Hradiš, Michal (referee) ; Kolář, Martin (advisor)
The main goal of this thesis is to implement and compare models based on various architectures of conditional generative adversarial networks. Their main purpose is to conditionally generate realistic looking human faces with selected features. Results from models using DCGAN, WGAN-GP and ProGAN architectures were compared. Models were implemented using Tensorflow library and were trained on Flickr-Faces-HQ dataset. Across all used architectures, I managed to train models capable of generating realistic human faces, with an option to select age and gender.
|
guest ::
