Fig. 1.

The architecture of the convolutional neural network used in DeepEM. The convolutional layer and the subsampling layer are abbreviated as C and S, respectively. C1:6@222×222 means that it is a convolutional layer and is the first layer of the network. This layer is comprised of six feature maps, each of which has a size of 222 × 222 pixels. The symbols and numbers above the feature maps of other layers have the equivalent corresponding meaning