CODEWITHSUNDEEP
pythontensorflowneural-networkdeep-learning
H42
H42

Reputation: 825

"TypeError: 'type' object is not subscriptable" when doing sess.run()

To better illustrate my question, I hereby use a very simple regression model (1 second run even by Gradient Descent).

I want to use a class reg_model() to contain my model. But when I run below code, I got the error TypeError: 'type' object is not subscriptable.

The error is from sess.run([reg_model['train_step'], reg_model['mean_square_loss']], feed_dict={x: training_set_inputs, yLb: training_set_outputs}). If I modified this code into sess.run([train_step, mean_square_loss], feed_dict={x: training_set_inputs, yLb: training_set_outputs}), and then remove the definition class reg_model():, then my code works well.

But I really want to use reg_model() to store the model, so that it can be a well defined object itself. How can I modify my code to achieve this?

import tensorflow as tf
import numpy as np

# values of training data
training_set_inputs =np.array([[0,1,2],[0,0,2],[1,1,1],[1,0,1]])
training_set_outputs =np.array([[1],[0],[1],[0]])

learning_rate = 0.5

class reg_model():

# containers and operations
    x = tf.placeholder(tf.float32, [None, 3])
    W = tf.Variable(tf.zeros([3, 1]))
    B = tf.Variable(tf.zeros([1]))

    yHat = tf.nn.sigmoid(tf.matmul(x, W) + B)
    yLb = tf.placeholder(tf.float32, [None, 1])

    mean_square_loss = tf.reduce_mean(tf.square(yLb - yHat)) 

    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(mean_square_loss)

# use session to execute graphs
with tf.Session() as sess:
    init=tf.global_variables_initializer()
    sess.run(init)

    # start training
    for i in range(10000):
        sess.run([reg_model['train_step'], reg_model['mean_square_loss']], feed_dict={x: training_set_inputs, yLb: training_set_outputs})

    # do prediction
    x0=np.float32(np.array([[0.,1.,0.]]))   
    y0=tf.nn.sigmoid(tf.matmul(x0,W) + B)

    print('%.15f' % sess.run(y0))

Upvotes: 2

Views: 2518

Answers (1)

mingaleg
mingaleg

Reputation: 2087

You should use reg_model.train_step and reg_model.mean_square_loss, not reg_model['train_step'] and reg_model['mean_square_loss']

Upvotes: 1

Related Questions