Machine learning

Klasifikacija slika pomoću CNN-a

CNN klasifikacija slika koristi duboke konvolucijske arhitekture kao što su ResNet (He i sur., 2016.), VGG i EfficientNet (Tan & Le, 2019.) za sortiranje slika u kategorije. Naslagani konvolucijski slojevi uče hijerarhiju vizualnih značajki izravno iz piksela, a preostale (rezidualne) veze sprječavaju problem nestajanja gradijenta u vrlo dubokim mrežama.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR. DOI: 10.1109/CVPR.2016.90
  2. Tan, M. & Le, Q.V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ICML, PMLR 97, 6105–6114. arXiv:1905.11946. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Convolutional Neural Network Image Classification (ResNet / VGG / EfficientNet). ScholarGate. https://scholargate.app/hr/deep-learning/cnn-image-classification

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateCNN Image Classification (Convolutional Neural Network Image Classification (ResNet / VGG / EfficientNet)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/cnn-image-classification · Skup podataka: https://doi.org/10.5281/zenodo.20539026