Hi

I am doing a regression following the tutorial RegressionKeras.py. The data that I have contains less than 100 entries. When I run the code I get the following error after the training and test are done at the `factory.EvaluateAllMethods()`

step:

```
1/1 [==============================] - 0s 9ms/step
1/1 [==============================] - 0s 9ms/step time left: 0 sec)
1/1 [==============================] - 0s 9ms/step
1/1 [==============================] - 0s 9ms/step
1/1 [==============================] - 0s 9ms/step
1/1 [==============================] - 0s 9ms/step
: Dataset[dataset] : Elapsed time for evaluation of 50 events: 2.33 sec
: Create variable histograms
: Create regression target histograms
: Create regression average deviation
: Results created
Factory : Evaluate all methods
: Evaluate regression method: PyKeras
: TestRegression (testing)
: Calculate regression for all events
1/1 [==============================] - 0s 9ms/step
*** Break *** floating point exception
===========================================================
There was a crash.
This is the entire stack trace of all threads:
===========================================================
```

It runs without problems if I do not do `EvaluateAllMethods()`

, but every time that either `nTrain_Regression`

or `nTest_Regression`

samples are less than 100, the `factory.EvaluateAllMethods()`

fails. Is there any way to solve this?

I have attached the RegressionKeras.py and the root file that I used to test that if I set train or the test sample is less than 100, the evaluation fails.

Thanks!

sampled_ReH_XMapCF_KM15_5pct.root (7.7 KB)

RegressionKeras.py (2.1 KB)