Figure 8 | Scientific Reports

Figure 8

From: Reconstruction of incomplete X-ray diffraction pole figures of oligocrystalline materials using deep learning

Figure 8

The basic reconstruction network architecture. It consists of three components: a convolutional encoder (ConvEncoder), transposed convolutional decoder (T-ConvDecoder), and a multilayer perceptron decoder (MLP-Decoder). The numbers show the dimension of output values per layer. We reshape the output of the MLP-Decoder to get the reconstructed unknown part of the pole plot for \(\psi _{\textrm{max}} = 60^\circ\).

Back to article page