///////////////////////////////////////////
// Running convGAN-majority-full on imblearn_webpage
///////////////////////////////////////////

Load 'data_input/imblearn_webpage'
from imblearn
non empty cut in data_input/imblearn_webpage! (76 points)
Data loaded.
-> Shuffling data
### Start exercise for synthetic point generator

====== Step 1/5 =======
-> Shuffling data
-> Spliting data to slices

------ Step 1/5: Slice 1/5 -------
-> Reset the GAN
Traceback (most recent call last):
  File "/benchmark/data/run_all_exercises.py", line 16, in <module>
    runExercise(dataset, None, name, generators[name])
  File "/benchmark/data/library/analysis.py", line 169, in runExercise
    avg = exercise.run(gan, data, resultsFileName=resultsFileName)
  File "/benchmark/data/library/exercise.py", line 127, in run
    self._exerciseWithDataSlice(gan, sliceData, imageFileName=imageFileName)
  File "/benchmark/data/library/exercise.py", line 166, in _exerciseWithDataSlice
    gan.reset(dataSlice.train)
  File "/benchmark/data/library/generators/convGAN.py", line 133, in reset
    self.conv_sample_generator = self._conv_sample_gen()
  File "/benchmark/data/library/generators/convGAN.py", line 237, in _conv_sample_gen
    x = Dense(self.neb * self.gen, activation='relu')(x)
  File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/usr/local/lib/python3.8/dist-packages/keras/backend.py", line 1920, in random_uniform
    return tf.random.uniform(
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[234600,614656] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu [Op:RandomUniform]