I created this function in order to save all values of the variable layer in an external file:
# Counter for total number of iterations performed so far
total_iterations = 0
def test_save(num_iterations):
# Ensure we update the global variable rather than a local copy
global total_iterations
for i in range(total_iterations, total_iterations + num_iterations):
x_batch, y_true_batch = next_batch_size(train_batch_size)
feed_dict_train = {x: x_batch, y_true: y_true_batch}
# Message for printing
msg = " Iteration: {0:>6}"
# Print it
print(msg.format(i + 1))
test = session.run(layer, feed_dict=feed_dict_train)
print 'test',test
store_all = []
store_all.append(test)
np.savetxt('test.txt', store_all, fmt='%5s')
# Call function
test_save(300)
# Placeholder variable for the input images
x = tf.placeholder(tf.float32, shape=[None, img_size_flat], name='x')
# Reshape 'x'
x_image = tf.reshape(x, [-1, img_size, img_size, num_channels])
# Placeholder variable for the true labels associated with the images
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
<tf.Tensor 'Conv2D_1:0' shape=(?, 16, 16, 1) dtype=float32>
You initializied an empty list at each iteration of your loop. Just put it outside :
# Counter for total number of iterations performed so far
total_iterations = 0
def test_save(num_iterations):
# Ensure we update the global variable rather than a local copy
global total_iterations
store_all = []
for i in range(total_iterations, total_iterations + num_iterations):
x_batch, y_true_batch = next_batch_size(train_batch_size)
feed_dict_train = {x: x_batch, y_true: y_true_batch}
# Message for printing
msg = " Iteration: {0:>6}"
# Print it
print(msg.format(i + 1))
test = session.run(layer, feed_dict=feed_dict_train)
print 'test',test
store_all.append(test)
np.savetxt('test.txt', store_all, fmt='%5s')
# Call function
test_save(300)