How to build a Recurrent Neural Network in TensorFlow (1/7)
Erik Hallström

Hello, thanks for your code, I have run the code, but if I set the truncated_backprop_length=15, the loss is always such huge, about 0.68, but I set it equals 30, the error goes down sharply, about 3.21224e-05.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.