user avatar
user avatar
user avatar
WDR
  • Member for 3 years, 4 months
  • Last seen more than a week ago
29 votes
2 answers
21k views

How to feed LSTM with different input array sizes?

20 votes
1 answer
20k views

What do "compile", "fit", and "predict" do in Keras sequential models?

19 votes
2 answers
19k views

What is the job of "RepeatVector" and "TimeDistributed"?

4 votes
3 answers
2k views

What is the difference between "Adding more LSTM layers" or "Adding more units on existence layers"?

4 votes
1 answer
181 views

Why my results have time delay when I use LSTM?

3 votes
1 answer
734 views

What are the output shape of LSTM with "return_sequences" equal to "True" or "False"?

3 votes
1 answer
233 views

What is the difference? "Adding more LSTM layers" or "Increasing epochs"?

2 votes
1 answer
7k views

Loss is decreasing but val_loss not! [duplicate]

2 votes
2 answers
4k views

loss/val_loss are decreasing but accuracies are the same in LSTM!

2 votes
1 answer
124 views

How can I specify I want output of which units in LSTM?

2 votes
1 answer
395 views

How to add previous predictions for new predictions in LSTM?

1 vote
1 answer
144 views

What is the difference between different batch_sizes in Keras Sequential models?

1 vote
1 answer
242 views

Is "adding the predictions to the real data for new training and prediction" a good idea for LSTM?

1 vote
1 answer
522 views

Is there any standard or normal range for the amount of LSTM loss function?

1 vote
0 answers
67 views

How does it work if we have different "time-steps" and "LSTM-units"?

1 vote
0 answers
12 views

Does LSTM just mocking previous data?

1 vote
1 answer
20 views

What does it mean: "Everything looks OK but loss won't decreases!"

1 vote
1 answer
3k views

How to design a many-to-many LSTM?

1 vote
2 answers
2k views

loss/val_loss decrease but acc/val_acc are consistent

1 vote
1 answer
194 views

What will happen if the number of units and the time-steps are different numbers in LSTM?

1 vote
1 answer
12k views

How to see/change learning rate in Keras LSTM?

1 vote
0 answers
3k views

What are best activation and regularization method for LSTM?

0 votes
1 answer
450 views

Why increasing the number of units or layers does not increase the accuracy and decrease the loss? [closed]

0 votes
1 answer
364 views

How can I access to loss value in Keras LSTM implementation?

0 votes
1 answer
302 views

Difference between "reducing batch_size" and "increasing epochs" to decrease loss amount?

0 votes
2 answers
4k views

Should we use only one-hot-vector for LSTM input/outputs?

0 votes
1 answer
1k views

How does the cost function of LSTM works? [closed]