I have a deep CNN network with 39 layers. While training the network is producing NaN output so the loss function is also producing NaN values. My network also has some custom layers which uses ‘dlconv’ where the weights are intialized using ‘initializeGlorot’ function. Why the network is producing ‘NaN’ outputs? Is there any way to solve this? Kindly request to provide suggestions.
Thanking,
BipinI have a deep CNN network with 39 layers. While training the network is producing NaN output so the loss function is also producing NaN values. My network also has some custom layers which uses ‘dlconv’ where the weights are intialized using ‘initializeGlorot’ function. Why the network is producing ‘NaN’ outputs? Is there any way to solve this? Kindly request to provide suggestions.
Thanking,
Bipin I have a deep CNN network with 39 layers. While training the network is producing NaN output so the loss function is also producing NaN values. My network also has some custom layers which uses ‘dlconv’ where the weights are intialized using ‘initializeGlorot’ function. Why the network is producing ‘NaN’ outputs? Is there any way to solve this? Kindly request to provide suggestions.
Thanking,
Bipin matlab, matlab gui, matlab code, deep learning, signal processing, digital signal processing, digital image processing, image processing, image, image analysis, image acquisition, image segmentation, signal, machine learning, matrix, matrices, matrix array, matrix manipulation, data, data preprocessing, deep learning toolbox, convolutional neural network, classification, class MATLAB Answers — New Questions

​