Training/Test data in tensorflow example - tensorflow

Question

I'm new in tensorflow and i follow example at here, but i have one question.
Codes are as follows:
import numpy as np
import tensorflow as tf
from time import time
import math
from include.data import get_data_set
from include.model import model, lr
train_x, train_y = get_data_set("train")
test_x, test_y = get_data_set("test")
x, y, output, y_pred_cls, global_step, learning_rate = model()
global_accuracy = 0
# PARAMS
_BATCH_SIZE = 128
_EPOCH = 60
_SAVE_PATH = "./tensorboard/cifar-10-v1.0.0/"
# LOSS AND OPTIMIZER
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=output, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate,
beta1=0.9,
beta2=0.999,
epsilon=1e-08).minimize(loss, global_step=global_step)
# PREDICTION AND ACCURACY CALCULATION
correct_prediction = tf.equal(y_pred_cls, tf.argmax(y, axis=1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# SAVER
merged = tf.summary.merge_all()
saver = tf.train.Saver()
sess = tf.Session()
train_writer = tf.summary.FileWriter(_SAVE_PATH, sess.graph)
try:
print("\nTrying to restore last checkpoint ...")
last_chk_path = tf.train.latest_checkpoint(checkpoint_dir=_SAVE_PATH)
saver.restore(sess, save_path=last_chk_path)
print("Restored checkpoint from:", last_chk_path)
except ValueError:
print("\nFailed to restore checkpoint. Initializing variables instead.")
sess.run(tf.global_variables_initializer())
def train(epoch):
batch_size = int(math.ceil(len(train_x) / _BATCH_SIZE))
i_global = 0
for s in range(batch_size):
batch_xs = train_x[s*_BATCH_SIZE: (s+1)*_BATCH_SIZE]
batch_ys = train_y[s*_BATCH_SIZE: (s+1)*_BATCH_SIZE]
start_time = time()
i_global, _, batch_loss, batch_acc = sess.run(
[global_step, optimizer, loss, accuracy],
feed_dict={x: batch_xs, y: batch_ys, learning_rate: lr(epoch)})
duration = time() - start_time
if s % 10 == 0:
percentage = int(round((s/batch_size)*100))
bar_len = 29
filled_len = int((bar_len*int(percentage))/100)
bar = '=' * filled_len + '>' + '-' * (bar_len - filled_len)
msg = "Global step: {:>5} - [{}] {:>3}% - acc: {:.4f} - loss: {:.4f} - {:.1f} sample/sec"
print(msg.format(i_global, bar, percentage, batch_acc, batch_loss, _BATCH_SIZE / duration))
test_and_save(i_global, epoch)
def test_and_save(_global_step, epoch):
global global_accuracy
i = 0
predicted_class = np.zeros(shape=len(test_x), dtype=np.int)
while i < len(test_x):
j = min(i + _BATCH_SIZE, len(test_x))
batch_xs = test_x[i:j, :]
batch_ys = test_y[i:j, :]
predicted_class[i:j] = sess.run(
y_pred_cls,
feed_dict={x: batch_xs, y: batch_ys, learning_rate: lr(epoch)}
)
i = j
correct = (np.argmax(test_y, axis=1) == predicted_class)
acc = correct.mean()*100
correct_numbers = correct.sum()
mes = "\nEpoch {} - accuracy: {:.2f}% ({}/{})"
print(mes.format((epoch+1), acc, correct_numbers, len(test_x)))
if global_accuracy != 0 and global_accuracy < acc:
summary = tf.Summary(value=[
tf.Summary.Value(tag="Accuracy/test", simple_value=acc),
])
train_writer.add_summary(summary, _global_step)
saver.save(sess, save_path=_SAVE_PATH, global_step=_global_step)
mes = "This epoch receive better accuracy: {:.2f} > {:.2f}. Saving session..."
print(mes.format(acc, global_accuracy))
global_accuracy = acc
elif global_accuracy == 0:
global_accuracy = acc
print("###########################################################################################################")
def main():
for i in range(_EPOCH):
print("\nEpoch: {0}/{1}\n".format((i+1), _EPOCH))
train(i)
if __name__ == "__main__":
main()
sess.close()
In this example, i think, both test and traning data feeds networks, normally only train data must feed network. I can not see any difference between train() and test_and_save() functions. Am i wrong? Thanks

Answer 1

Here is an explanation if I understood your question correctly. The train function is called every epoch and iterates through the training data. At the end of the epoch the test_and_save function is called where the model accuracy is evaluated. This iterates through the test data on the learned weights and calculates the accuracy and saves the model. This is repeated _EPOCH times.
Edit: The model is saved in the test_and_save function. However, the weights are only updated (gradients calculated) when optimizer is passed through sess.run() in the train function. In the test_and_save function the test data is fed to the network however only y_pred_cls is evaluated by passing to sess.run().