How to merge the train, test and validation set of mnist in tensorflow for batch training. Anyone can help me?
Asked
Active
Viewed 1,149 times
0
-
Details, please? – Siegmeyer Aug 17 '17 at 15:32
-
1I want to mix the train, test and validation set for unsupervised feature learning in tensorflow. The mixed dataset is fed to the network (e.g. AutoEncoder) for batch processing. – Qiang Wang Aug 18 '17 at 00:49
1 Answers
0
What would be the purpose of using a testing set to train a model... Then it would become a training set too.
Sets are named training, validation and testing for a reason.
So you train your model with the training data. Once the model is trained, you validate it over the validation data. You test the performance of the model over the testing data. The training method you use (batch or something else) will NEVER change the fact that training/validation/testing data should never be mixed with one another.
If this does not answer your question, then edit your question and specify, because it is rather vague at the present moment.
Eskapp
- 3,419
- 2
- 22
- 39
-
-
1@JwalantBhatt You don't do cross-validation with deep learning. Cross-validation is used when the data sets are too small to have separate training/validation/testing sets. This is never the case when you use deep learning. The training cost for a DNN is also prohibitive for doing cross-validation. – Eskapp Oct 12 '18 at 21:06