Tensorflow error: Failed to convert object of type <class 'dict'> to Tensor

Question

I am trying to code a neural network which can recognize handwritten digits. I am using the MNIST dataset and the tensor flow library. For now, I am only trying to train the network but it throws a huge error whenever I run it. I am a beginner, so I am very sorry if the code looks bad.

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("/tmp/data", one_hot = True)
numNodesH1 = 600
numNodesH2 = 500
numNodesH3 = 500
numNodesOut = 10
sizeOfBatch = 150

y = tf.placeholder("float")
x = tf.placeholder("float", [None, 784])

def neuralNetwork(value):
    H1 = {'weights': tf.Variable(tf.random_normal([784, numNodesH1])),
         "biases": tf.Variable(tf.random_normal([numNodesH1]))}

    H2 = {'weights': tf.Variable(tf.random_normal([numNodesH1, 
         numNodesH2])),
         "biases": tf.Variable(tf.random_normal([numNodesH2]))}

    H3 = {"weights": tf.Variable(tf.random_normal([numNodesH2, 
    numNodesH3])),
    "biases": tf.Variable(tf.random_normal([numNodesH3]))}

    output = {"weights": tf.Variable(tf.random_normal([numNodesH3, 
    numNodesOut])),
    "biases": tf.Variable(tf.random_normal([numNodesOut]))}

    FinalH1 = tf.add(tf.matmul(value, H1["weights"]), H1["biases"])
    FinalH1 = tf.nn.relu(FinalH1)
    FinalH2 = tf.add(tf.matmul(H1, H2["weights"]), H2["biases"])
    FinalH2 = tf.nn.relu(FinalH2)
    FinalH3 = tf.add(tf.matmul(H2, H3["weights"]), H3["biases"])
    FinalH3 = tf.nn.relu(FinalH3)
    FinalOut = tf.matmul(H3, output["weights"]) + output["biases"]

    return FinalOut

def train(inputdata):
    prediction = neuralNetwork(inputdata)
    cost=tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
    optimizingTool = tf.train.AdamOptimizer().minimize(cost)
    epochsNum = 10

    with tf.Session as sess:
        sess.run(tf.global_variables_initializer())

        for i in range(epochsNum):
            lostEpochs = 0
            for o in range(int(mnist.train.num_examples / sizeOfBatch)):
                ex, ey = mnist.train.next_batch(sizeOfBatch)
                _, c = sess.run([optimizer, cost], feed_dict = {x: ex, y: 
                                ey})
                lostEpochs = lostEpochs + c

            print("Epochs completed = ", i, " / ", epochsNum, " epoch loss = 
            ", lostEpochs)

    correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
    neuralAccuracy = tf.reduce_mean(tf.cast(correct, "float"))
    print(neuralAccuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

train(x)

Every time I run this code, it gives me this error:

Traceback (most recent call last):
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\framework\tensor_util.py", line 468, in 
make_tensor_proto
str_values = [compat.as_bytes(x) for x in proto_values]
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\framework\tensor_util.py", line 468, in 
<listcomp>
str_values = [compat.as_bytes(x) for x in proto_values]
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\util\compat.py", line 65, in as_bytes
(bytes_or_text,))
TypeError: Expected binary or unicode string, got {'weights': <tf.Variable 
'Variable:0' shape=(784, 600) dtype=float32_ref>, 'biases': <tf.Variable 
'Variable_1:0' shape=(600,) dtype=float32_ref>}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\Msi-
\AppData\Local\Programs\Python\Python36\neuralnetworktest.py", line 45, in 
<module>
train(x)
File "C:\Users\Msi-
\AppData\Local\Programs\Python\Python36\neuralnetworktest.py", line 29, in 
train
prediction = neuralNetwork(inputdata)
File "C:\Users\Msi-
\AppData\Local\Programs\Python\Python36\neuralnetworktest.py", line 22, in 
neuralNetwork
FinalH2 = tf.add(tf.matmul(H1, H2["weights"]), H2["biases"])
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\ops\math_ops.py", line 1844, in matmul
a = ops.convert_to_tensor(a, name="a")
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\framework\ops.py", line 836, in convert_to_tensor
as_ref=False)
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\framework\ops.py", line 926, in 
internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\framework\constant_op.py", line 229, in 
_constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\framework\constant_op.py", line 208, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\lib\site-
packages\tensorflow\python\framework\tensor_util.py", line 472, in 
make_tensor_proto
"supported type." % (type(values), values))
TypeError: Failed to convert object of type <class 'dict'> to Tensor. 
Contents: 
{'weights': <tf.Variable 'Variable:0' shape=(784, 600) dtype=float32_ref>, 
'biases': <tf.Variable 'Variable_1:0' shape=(600,) dtype=float32_ref>}. 
Consider 
casting elements to a supported type.

As a side note. If you are using the standard NMIST dataset you have 60000 images for training. Now you have a huge network, and you are dealing with roughly with one million (rounded) parameters. I would check overfitting... Why such a big network? With just the softmax function as output you get already over 92%... Just saying... — Umberto
– Umberto, Commented Jan 9, 2018 at 14:02

Maxim · Accepted Answer · 2018-01-09 12:05:08Z

3

I think you meant

FinalH1 = tf.add(tf.matmul(value, H1["weights"]), H1["biases"])
FinalH1 = tf.nn.relu(FinalH1)
FinalH2 = tf.add(tf.matmul(FinalH1, H2["weights"]), H2["biases"])
FinalH2 = tf.nn.relu(FinalH2)
FinalH3 = tf.add(tf.matmul(FinalH2, H3["weights"]), H3["biases"])
FinalH3 = tf.nn.relu(FinalH3)
FinalOut = tf.matmul(FinalH3, output["weights"]) + output["biases"]

Note FinalH1 instead of H1 and that same for H2 and H3.

edited Jan 9, 2018 at 12:05

answered Jan 8, 2018 at 12:14

Maxim

53.9k27 gold badges161 silver badges213 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

LeoTheDev Over a year ago

Now it says: Traceback (most recent call last): File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\neuralnetworktest.py", line 44, in <module> train(x) File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\neuralnetworktest.py", line 28, in train prediction = neuralNetwork(inputdata) File "C:\Users\Msi-\AppData\Local\Programs\Python\Python36\neuralnetworktest.py", line 20, in neuralNetwork FinalH1 = tf.nn.relu(FinalH1) UnboundLocalError: local variable 'FinalH1' referenced before assignment

Maxim Over a year ago

You've removed the first line: FinalH1 = tf.add(tf.matmul(value, H1["weights"]), H1["biases"]). It is correct, so I didn't include it into the snippet. Return it back

Collectives™ on Stack Overflow

Tensorflow error: Failed to convert object of type <class 'dict'> to Tensor

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related