I want to create a batch generator for training purposes - unfortunately I don't know how to make it so that the generator proceeds to the next time steps after it has finished a batch. That is, if the batch has processed say [0 1 2 3 4], it then has to process the next [5 6 7 8 9] of the whole say [0 1 2 ... 100] training set.
I also want that one epoch is one pass through the entire batch - so the batch generator has to go back at the beginning of the training set.
From keras.io, I have read that the if default epoch_steps=None, then "is equal to the number of samples in your dataset divided by the batch size, or 1 if that cannot be determined".
def batch_generator(batch_size, sequence_length):
"""
Generator function for creating batches of training-data.
"""
# Infinite loop.""
while True:
# Allocate a new array for the batch of input-signals.
x_shape = (batch_size, sequence_length, num_x_signals)
x_batch = np.zeros(shape=x_shape, dtype=np.float16)
# Allocate a new array for the batch of output-signals.
y_shape = (batch_size, sequence_length, num_y_signals)
y_batch = np.zeros(shape=y_shape, dtype=np.float16)
# Fill the batch with random sequences of data.
for i in range(batch_size):
# Copy the sequences of data starting at this index.
x_batch[i] = x_train_scaled[:sequence_length]
y_batch[i] = y_train_scaled[:sequence_length]
x_batch_1 = x_batch[ :, :, 0:5]
x_batch_2 = x_batch[ :, :, 5:12]
yield ([x_batch_1, x_batch_2], y_batch)
batch_size = 32
sequence_length = 24 * 7
generator = batch_generator(batch_size=batch_size,
sequence_length=sequence_length)
%%time
model.fit_generator(generator=generator,
epochs=10,
steps_per_epoch=None,
validation_data=validation_data,
callbacks=callbacks)
