dnn_tensorflow_cpp
dnn_tensorflow_cpp copied to clipboard
This project is a simple deep neural network trained using only TensorFlow C++.
Hey there, I am implementing a multilayer perceptron with the AddSymbolicGradients, for the or and x-or it works with multiclass but for mnist data it doesnt train the loss for...
i am just trying to make something a little bit easier for someone to take interest or you can ignore this PR

i just build the program well when the program run to the line 90: TF_CHECK_OK(session.Run({{x, x_data}, {y, y_data}}, {apply_w1, apply_w2, apply_w3, apply_b1, apply_b2, apply_b3}, nullptr)); the system always told me...
Very instructive work