CODEWITHSUNDEEP
pythonimage-processingtensorflowneural-network
raph
raph

Reputation: 319

Getting error 'Too Many Values To Unpack' while looping over tensors; unable to use tf.train.batch

When I initialize my Neural Net:

print('Checking the Training on a Single Batch...')
with tf.Session() as sess:
    # Initializing the variables
    sess.run(tf.global_variables_initializer())

    # Training cycle
    for epoch in range(epochs):
        batch_i = 1
        for batch_features, batch_labels in (input_data, input_labels):
            train_neural_network(sess, optimizer, keep_probability, batch_features, batch_labels)
        print('Epoch {:>2}, Batch {}:  '.format(epoch + 1, batch_i), end='')
        print_stats(sess, batch_features, batch_labels, cost, accuracy)

I get ValueError: too many values to unpack (expected 2) on the For Loop.

I figured it might be because I didn't create batches, so I created:

tf.train.batch([input_data, input_labels], batch_size, num_threads=1, capacity=32)

But I get error:

TypeError: Cannot convert a list containing a tensor of dtype <dtype: 'uint8'> to <dtype: 'float32'> (Tensor is: <tf.Tensor 'stack_16495:0' shape=(280, 440, 3) dtype=uint8>)

Both input_data / input_labels is a list of tensors of arrays created using tf.stack.

Upvotes: 0

Views: 1077

Answers (1)

kvorobiev
kvorobiev

Reputation: 5070

ValueError: caused by statement

for batch_features, batch_labels in (input_data, input_labels):

you needs 

for batch_features, batch_labels in zip(input_data, input_labels):

instead. (input_data, input_labels) results in tuple with two elements - input_data and input_labels. zip creates list of tuples with elements from input_data and input_labels.
Small example with code

a = [1,2,3]
b = ['a', 'b', 'c']
c = (a, b)
d = zip(a, b)
c
Out[16]: ([1, 2, 3], ['a', 'b', 'c'])
d
Out[17]: [(1, 'a'), (2, 'b'), (3, 'c')]

Upvotes: 1

Related Questions