我正在尝试sae.dnn.train()包含5000个案例，55个输入和3个隐藏图层。
为什么函数nn.predict返回NaN？ （载体）
我正在使用以下命令
Nrow <-5000
Ncol <- 55
v <- c(rnorm(Nrow*Ncol,1, 0.5))
x <- matrix(v, nrow=Nrow, ncol=Ncol)
y <- c(rep(1, Nrow/2), rep(0, Nrow/2))
dnn <- sae.dnn.train(x, y, hidden = c(100,90,80),activationfun = "tanh", learningrate = 0.6, momentum = 0.5, learningrate_scale = 1.0,output = "sigm", sae_output = "linear", numepochs = 10, batchsize = 100, hidden_dropout = 0, visible_dropout = 0)
yy <- nn.predict(dnn, x)