Big Data vs Smart Data on the Generation of Floor Plans with Deep Learning

Big Data vs Smart Data on the Generation of Floor Plans with Deep Learning

Imagawa, Marcelo Kenzo; Koga, Renan Rubio; Duarte, Rovenir Bertola; Rodrigues, Ricardo Cesar

Full Article:

Due to the progressive growth of data dimensionality, addressing how much data and time is required to train deep learning models has become an important research topic. Thus, in this paper, we present a benchmark for generating floor plans with Conditional Generative Adversarial Networks in which we compare 10 trained models on a dataset of 80.000 samples, the models use different data dimensions and hyper-parameters on the training phase, beyond this objective, we also tested the capability of Convolutional Neural Networks (CNN) to reduce the dataset noise. The models' assessment was made on more than 6 million with the Frétche Inception Distance (FID). The results show that such models can rapidly achieve similar or even better FID results if trained with 800 images of 512x512 pixels, in comparison to high dimensional datasets of 256x256 pixels, however, using CNNs to enhance data consistency reproduced optimal results using around 27.000 images

Due to the progressive growth of data dimensionality, addressing how much data and time is required to train deep learning models has become an important research topic. Thus, in this paper, we present a benchmark for generating floor plans with Conditional Generative Adversarial Networks in which we compare 10 trained models on a dataset of 80.000 samples, the models use different data dimensions and hyper-parameters on the training phase, beyond this objective, we also tested the capability of Convolutional Neural Networks (CNN) to reduce the dataset noise. The models' assessment was made on more than 6 million with the Frétche Inception Distance (FID). The results show that such models can rapidly achieve similar or even better FID results if trained with 800 images of 512x512 pixels, in comparison to high dimensional datasets of 256x256 pixels, however, using CNNs to enhance data consistency reproduced optimal results using around 27.000 images

Palavras-chave:

DOI: 10.5151/sigradi2021-114

Referências bibliográficas

• [1]

Como citar:

Imagawa, Marcelo Kenzo; Koga, Renan Rubio; Duarte, Rovenir Bertola; Ricardo Cesar Rodrigues; "Big Data vs Smart Data on the Generation of Floor Plans with Deep Learning", p-217-228. In: XXV International Conference of the Iberoamerican Society of Digital Graphics. São Paulo: Blucher, 2021.
ISSN 23186968, DOI 10.5151/sigradi2021-114