import tensorflow as tf
import numpy as np
import timeit
def regress_without_tfData(n_epochs, input_dimension, training_inputs, training_labels):
tf.reset_default_graph()
weights = tf.get_variable("weights", initializer=np.random.randn(input_dimension, 1).astype(np.float32))
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for _ in range(n_epochs):
sess.run(loss_op, feed_dict={X: training_inputs, Y:training_labels})
X,Y = data_set.make_one_shot_iterator().get_next()
prediction = tf.matmul(X, weights)
loss = tf.reduce_mean(tf.square(tf.subtract(prediction, Y)))
loss_op = tf.train.AdamOptimizer(.01).minimize(loss)
init = tf.global_variables_initializer()
for input_dimension in input_dimensions_list:
for data_size in [500, 100000]:
training_inputs = np.random.randn(data_size, input_dimension).astype(np.float32)
random_covector = np.random.randint(-5, 5, size=(input_dimension, 1))
training_labels = function_to_approximate(training_inputs)
for input_dimension in input_dimensions_list:
for data_size, batch_size in [(500, 50), (500, 500), (100000, 50), (100000, 100000)]:
training_inputs = np.random.randn(data_size, input_dimension).astype(np.float32)
random_covector = np.random.randint(-5, 5, size=(input_dimension, 1))
training_labels = function_to_approximate(training_inputs)
data_set = tf.data.Dataset.from_tensor_slices((training_inputs, training_labels))
data_set = data_set.repeat(n_epochs)
data_set = data_set.batch(batch_size)
Not using tf.data, with data size 500, input dimension 10 and training with a full batch, it took an average of 0.20243382899980134 seconds to run 10 epochs.
Not using tf.data, with data size 100000, input dimension 10 and training with a full batch, it took an average of 0.2431719040000644 seconds to run 10 epochs.
Using tf.data, with data size 500, and input dimension 10, and training with batch size 50, it took an average of 0.09512088866661846 seconds to run 10 epochs.
Using tf.data, with data size 500, and input dimension 10, and training with batch size 500, it took an average of 0.07286913600000844 seconds to run 10 epochs.
Using tf.data, with data size 100000, and input dimension 10, and training with batch size 50, it took an average of 4.421892363666605 seconds to run 10 epochs.
Using tf.data, with data size 100000, and input dimension 10, and training with batch size 100000, it took an average of 2.2555197536667038 seconds to run 10 epochs.