Skip to main content
Visual Computing for Industry, Biomedicine, and Art
Fig. 3 | Visual Computing for Industry, Biomedicine, and Art

Fig. 3

From: Discrimination between leucine-rich glioma-inactivated 1 antibody encephalitis and gamma-aminobutyric acid B receptor antibody encephalitis based on ResNet18

Fig. 3

Architecture of the ResNet18 (a), VGG16 (b) and ResNet50 (c). For each of the CNN models, a zero-padding layer was added before the first convolution layer, so that the size of the image fed into the first convolution layer was 224 × 224. The number of the input channel in the first convolution layer was set to one. The output dimension of the fully connected layer was set to two. Conv: Convolution layer; ReLU: Rectified linear unit

Back to article page