Puntuación de precisión Tensorflow (simple)

Tengo un conjunto de datos que tiene un formato similar al conjunto de datos de Iris y me gustaría usar un clasificador personalizado para analizarlo.

Como no soy muy bueno con Python, estoy adaptando el código de otra persona, gracias :), que ha funcionado muy bien hasta ahora. Sin embargo, quiero agregar un puntaje de precisión ya que mi conjunto de datos tiene más de 1 millón de puntos de datos y acabo de resolverlo.

El código que estoy usando es:

# Dependencies
import tensorflow as tf
import pandas as pd
import numpy as np

print(tf.__version__)

# Make results reproducible
seed = 1234
np.random.seed(seed)
tf.set_random_seed(seed)

# Loading the dataset
dataset = pd.read_csv('Iris_Dataset.csv')
dataset = pd.get_dummies(dataset, columns=['Species']) # One Hot Encoding
values = list(dataset.columns.values)

#y is the CellType value x is the data
# Python is a 0 index language
y = dataset[values[-3:]]
y = np.array(y, dtype='float32')
X = dataset[values[1:-3]]
X = np.array(X, dtype='float32')

# Shuffle Data
indices = np.random.choice(len(X), len(X), replace=False)
X_values = X[indices]
y_values = y[indices]

# Creating a Train and a Test Dataset
test_size = 10
X_test = X_values[-test_size:]
X_train = X_values[:-test_size]
y_test = y_values[-test_size:]
y_train = y_values[:-test_size]

# Session
sess = tf.Session()

# Interval / Epochs
interval = 50
epoch = 500

# Initialize placeholders
X_data = tf.placeholder(shape=[None, 4], dtype=tf.float32)
y_target = tf.placeholder(shape=[None, 3], dtype=tf.float32)

# Input neurons : 4
# Hidden neurons : 8
# Output neurons : 3
hidden_layer_nodes = 9

# Create variables for Neural Network layers
w1 = tf.Variable(tf.random_normal(shape=[4,hidden_layer_nodes])) # Inputs -> Hidden Layer
b1 = tf.Variable(tf.random_normal(shape=[hidden_layer_nodes]))   # First Bias
w2 = tf.Variable(tf.random_normal(shape=[hidden_layer_nodes,3])) # Hidden layer -> Outputs
b2 = tf.Variable(tf.random_normal(shape=[3]))   # Second Bias

# Operations
hidden_output = tf.nn.relu(tf.add(tf.matmul(X_data, w1), b1))
final_output = tf.nn.softmax(tf.add(tf.matmul(hidden_output, w2), b2))

# Cost Function
loss = tf.reduce_mean(-tf.reduce_sum(y_target * tf.log(final_output), axis=0))

# Optimizer
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(loss)

# Initialize variables
init = tf.global_variables_initializer()
sess.run(init)

# Training
print('Training the model...')
for i in range(1, (epoch + 1)):
    sess.run(optimizer, feed_dict={X_data: X_train, y_target: y_train})
    if i % interval == 0:
        print('Epoch', i, '|', 'Loss:', sess.run(loss, feed_dict={X_data: X_train, y_target: y_train}))

# Prediction
print()
for i in range(len(X_test)):
    print('Actual:', y_test[i], 'Predicted:', np.rint(sess.run(final_output, feed_dict={X_data: [X_test[i]]})))

# Evaluate accuracy.
accuracy_score = y_target.evaluate(input_fn=y_target)["accuracy"]

print("\nTest Accuracy: {0:f}\n".format(accuracy_score))

El resultado que obtengo es

1.4.0
2018-04-05 09:06:35.688295: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
Training the model...
Epoch 50 | Loss: 11.3519
Epoch 100 | Loss: 7.53955
Epoch 150 | Loss: 6.3168
Epoch 200 | Loss: 5.58197
Epoch 250 | Loss: 5.09148
Epoch 300 | Loss: 4.74129
Epoch 350 | Loss: 4.47681
Epoch 400 | Loss: 4.26831
Epoch 450 | Loss: 4.09931
Epoch 500 | Loss: 3.95926

Actual: [ 0.  0.  1.] Predicted: [[ 0.  0.  1.]]
Actual: [ 1.  0.  0.] Predicted: [[ 1.  0.  0.]]
Actual: [ 0.  0.  1.] Predicted: [[ 0.  0.  1.]]
Actual: [ 1.  0.  0.] Predicted: [[ 1.  0.  0.]]
Actual: [ 1.  0.  0.] Predicted: [[ 1.  0.  0.]]
Actual: [ 0.  0.  1.] Predicted: [[ 0.  0.  1.]]
Actual: [ 0.  0.  1.] Predicted: [[ 0.  0.  1.]]
Actual: [ 0.  1.  0.] Predicted: [[ 0.  1.  0.]]
Actual: [ 1.  0.  0.] Predicted: [[ 1.  0.  0.]]
Actual: [ 1.  0.  0.] Predicted: [[ 1.  0.  0.]]
Traceback (most recent call last):
  File "/Users/XXXX/PycharmProjects/TensorFlow1/Iris/Iris_Network.py", line 86, in <module>
    accuracy_score = y_target.evaluate(input_fn=y_target)["accuracy"]
AttributeError: 'Tensor' object has no attribute 'evaluate'

Process finished with exit code 1

Como puede ver, solo las dos últimas líneas de código son incorrectas. ¿Cuáles deberían ser estos?