def shuffle_data_samples(GraphData):
''' Shuffle Data
'''
GraphData.train_input_data, GraphData.train_output_data = data.shuffle_input_output(
GraphData.train_input_data, GraphData.train_output_data)
GraphData.val_input_data, GraphData.val_output_data = data.shuffle_input_output(
GraphData.val_input_data, GraphData.val_output_data)
GraphData.eval_input_data, GraphData.eval_output_data = data.shuffle_input_output(
GraphData.eval_input_data, GraphData.eval_output_data)
def reset_train_batches(self, batch_size=None, num_batches=None):
''' This function resets the training batches
Example: Training data set = 1000 samples,
Batch size = 300
Framework: Keras
- The output is an array of as many training samples that fit within the batch size.
Train_input_batches.shape = [900, data_size]
Framework: Tensorflow
- The Tensorflow implementation requires each mini-batch to be explicitly set.
Train_input_batches.shape = (# batches, ) - In each batch is a numpy array of size (batch_size, data_size)
:param batch_size:
:param num_batches:
:return:
'''
# Update batch size if passed
if batch_size is not None:
self.batch_size = batch_size
# Calc number of batches
if num_batches is not None:
self.num_train_batches = int(num_batches)
else:
self.num_train_batches = int(
np.floor(self.train_input_data.shape[0] / self.batch_size))
# Copy all training data
self.train_input_batches = self.train_input_data
self.train_output_batches = self.train_output_data
# Shuffle Training data
self.train_input_batches, self.train_output_batches = data.shuffle_input_output(
self.train_input_batches, self.train_output_batches)
## Restrict the amount of training Data a number that fits in the number of batches
self.train_input_batches = self.train_input_batches[:self.batch_size *
self.
num_train_batches]
self.train_output_batches = self.train_output_batches[:self.
batch_size *
self.
num_train_batches]
if self.frame_work == 'Keras':
return
if self.frame_work == 'Tensorflow':
self.train_input_batches, self.train_output_batches = data.convert_to_tensorflow_minbatch(
self.train_input_batches, self.train_output_batches,
self.batch_size)
def split_train_val_eval(self, val_split=0.3, eval_split=0, shuffle=False):
if shuffle == True:
self.all_input_data, self.all_output_data = data.shuffle_input_output(
self.all_input_data, self.all_output_data)
total_samples = int(self.all_input_data.shape[0])
# Split into training/validation/evaluation data
self.eval_samples = int(self.all_input_data.shape[0] * eval_split)
self.val_samples = int(self.all_input_data.shape[0] * val_split)
self.train_samples = int(self.all_input_data.shape[0] -
self.eval_samples - self.val_samples)
print(
'Train Samples = {}({}%), Val Samples = {}({}%), Eval Samples = {}({}%)'
.format(self.train_samples,
np.round(self.train_samples / total_samples * 100,
2), self.val_samples,
np.round(self.val_samples / total_samples * 100, 2),
self.eval_samples,
np.round(self.eval_samples / total_samples * 100, 2)))
self.eval_input_data = self.all_input_data[total_samples -
self.eval_samples:]
self.eval_output_data = self.all_output_data[total_samples -
self.eval_samples:]
self.val_input_data = self.all_input_data[total_samples -
self.eval_samples - self.
val_samples:total_samples -
self.eval_samples]
self.val_output_data = self.all_output_data[total_samples -
self.eval_samples - self.
val_samples:total_samples -
self.eval_samples]
self.train_input_data = self.all_input_data[:total_samples -
self.eval_samples -
self.val_samples]
self.train_output_data = self.all_output_data[:total_samples -
self.eval_samples -
self.val_samples]
def shuffle_training_only(self):
print('Shuffling Training Data')
self.train_input_data, self.train_output_data = data.shuffle_input_output(
self.train_input_data, self.train_output_data)
