LSTM only train once using keras

Question

I'm trying to train a LSTM model to predict the temperature.but the model only got trained in first epochs.

I got the usage and temperature of cpu from a server in about twenty hours as the dataset.I want to predict the temperature of cpu after 10m by using 10m's data before.so I reshape my dataset to (1301,10,2) as I have 1301 samples,10m timesteps and 2 features, then I divide it to 1201 and 100 as the train dataset and the validation dataset.

I check the dataset manually,so it should be right.

I creat the LSTM model as below

    model = Sequential()
    model.add(LSTM(10, activation="relu", input_shape=(train_x.shape[1], train_x.shape[2]),return_sequences=True))
    model.add(Flatten())
    model.add(Dense(1, activation="softmax"))
    model.compile(loss='mean_absolute_error', optimizer='RMSprop')

and try to fit it

    model.fit(train_x, train_y, epochs=50, batch_size=32, validation_data=(test_x, test_y), verbose=2)

I got the log like this:

Epoch 1/50
 - 1s - loss: 0.8016 - val_loss: 0.8147
Epoch 2/50
 - 0s - loss: 0.8016 - val_loss: 0.8147
Epoch 3/50
 - 0s - loss: 0.8016 - val_loss: 0.8147
Epoch 4/50
 - 0s - loss: 0.8016 - val_loss: 0.8147
Epoch 5/50
 - 0s - loss: 0.8016 - val_loss: 0.8147
Epoch 6/50
 - 0s - loss: 0.8016 - val_loss: 0.8147
Epoch 7/50
 - 0s - loss: 0.8016 - val_loss: 0.8147
Epoch 8/50
 - 0s - loss: 0.8016 - val_loss: 0.8147
Epoch 9/50
 - 0s - loss: 0.8016 - val_loss: 0.8147

The trainning time of each epoch is 0 expect the first epoch,and the loss never decrease.I tried changing the number of LSTM cells,loss function and optimizer,but it still don't work.

The key to the problem is that the unit number of your last layer is 1. The result of 'tf.nn.softmax' are all the same .You can refer [Neural Network with Tensorflow doesn't update weights/bias](https://stackoverflow.com/questions/55214395/neural-network-with-tensorflow-doesnt-update-weights-bias/55215362#55215362) — giser_yugang, Jul 17 '19 at 02:01

score 0 · Answer 1 · answered Jul 18 '19 at 01:26

0

Changing the activation function of last layer from softmax to sigmoid make the model works.Thanks to @giser_yugang @Ashwin Geet D'Sa

answered Jul 18 '19 at 01:26

yf.kang

1

LSTM only train once using keras

1 Answers1