Fig. 2From: Dose prediction for cervical cancer VMAT patients with a full-scale 3D-cGAN-based model and the comparison of different input data on the prediction resultsThe architecture of the discriminator contains a total of 3 convolution layers with a stride of 2 and two convolution layers with a stride of 1, as well as the related normalization layer and activation layer. Each element in the 3D probability value matrixes has a 70*70*70 receptive fieldBack to article page