Good evening. Where can I find the learning rate in the code to change it? Thank you

I guess, this is because custom optimizer is not good for providing best result. Therefore they left original ADAM optimizer.

Hi, you can check the resources for assignment MNIST - Exercises, there is a described solution for adjusting the learning rate.

I have looked for it in the "Tensorflow MNIST complete with comments", but I can't find the learning rate. Are you able to find the line of code with the learning rate?

Once you download these resources > go to MNIST - Exercises.zip > 12_8_mnist-exercises-solutions.rar > folder MNIST - Exercise Solutions > 8. TensorFlow_MNIST_Learning_rate_Part_1_Solution.ipynb You will see the described solution. Basically it is just this code: custom_optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001) model.compile(optimizer=custom_optimizer, loss='sparse_categorical_crossentropy', metrics=['accuracy'])