CODEWITHSUNDEEP
pythontensorflow
Engine
Engine

Reputation: 5432

Error - Cannot feed value of shape X for Tensor

I've run all the examples on the Tensorflow page, using the MNIST database. Now I'm trying to run my own example and I really just don't get it.

Say I have this csv table:

enter image description here

It has like 5000 rows. and the last column is the label for each row, this one is composed of multiple features. Now for my first concrete example. I want to train a NN on this data, for that here what I've done: 

    import tensorflow as tf
    import  numpy as np
    import  csv
    import os
    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
    # read training data
    Training_file  = open('onetest.csv', 'r', newline='')
    reader = csv.reader(Training_file)
    row = next(reader)
    number_of_rows = 2431
    x = tf.placeholder('float',[None,len(row[:-1])])
    w = tf.Variable(tf.zeros([len(row[:-1]),25]))
    b = tf.Variable(tf.zeros([25]))
    model = tf.add(tf.matmul(x,w),b)
    y_ = tf.placeholder('float',[25,None])
    y =  tf.nn.softmax(model)

    cross_entropy= -tf.reduce_sum(y_*tf.log(y))
    train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
    sess = tf.Session()
    sess.run(tf.global_variables_initializer())
    index =1
    batch_xs =[]
    batch_ys= []
    for row in reader:
        batch_xs.append(row[:-1])
        batch_ys.append(row[-1])
        print(len(batch_xs),len(batch_ys))
        index +=1
        if index%10==0:
            sess.run(train_step,feed_dict={x:batch_xs, y_:batch_ys})
            correct_prediction = tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1))
            accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
            batch_xs.clear();
            batch_ys.clear();

Here is there error that I get :

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-11-4dbaa38c4d9c> in <module>()
     29     index +=1
     30     if index%10==0:
---> 31         sess.run(train_step,feed_dict={x:batch_xs, y_:batch_ys})
     32         correct_prediction = tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1))
     33         accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))

c:\users\engine\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
    765     try:
    766       result = self._run(None, fetches, feed_dict, options_ptr,
--> 767                          run_metadata_ptr)
    768       if run_metadata:
    769         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

c:\users\engine\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
    942                 'Cannot feed value of shape %r for Tensor %r, '
    943                 'which has shape %r'
--> 944                 % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
    945           if not self.graph.is_feedable(subfeed_t):
    946             raise ValueError('Tensor %s may not be fed.' % subfeed_t)

ValueError: Cannot feed value of shape (9,) for Tensor 'Placeholder_17:0', which has shape '(25, ?)'

I've change the value of the index but it didn't solve it so I guess I'm misunderstanding something. will be grateful for any explanation.

Upvotes: 0

Views: 561

Answers (2)

Miriam Farber
Miriam Farber

Reputation: 19634

In this row y_ = tf.placeholder('float',[25,None]), y_ is defined to be a placeholder for data that has 25 rows (and any number of columns). Then in your code, due to the row if index%10==0: your batch_ys has 10 rows, which is the reason that you get this error.

Upvotes: 1

Engine
Engine

Reputation: 5432

So I got it, here is the cod for that, it may help somebody out there : 

    import tensorflow as tf
import  numpy as np
import  csv
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
# read training data
Training_file  = open('onetest.csv', 'r', newline='')
reader = csv.reader(Training_file)
row = next(reader)

x = tf.placeholder('float',[None,len(row[:-1])])
w = tf.Variable(tf.zeros([len(row[:-1]),25]))
b = tf.Variable(tf.zeros([25]))
model = tf.add(tf.matmul(x,w),b)
y_ = tf.placeholder('float',[None,25])
y =  tf.nn.softmax(model)
print(y)

cross_entropy= -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
index =0
batch_xs =[]
ys= []
for row in reader:
    batch_xs.append(row[:-1])
    ys.append(row[-1])

    index +=1
    if index%25==0:
            batch_ys = np.reshape(ys,(1,25))

            sess.run(train_step,feed_dict={x:batch_xs,y_:batch_ys})
            correct_prediction = tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1))
            accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
            print(sess.run(accuracy,feed_dict={x:batch_xs,y_:batch_ys}))
            batch_xs.clear()
            ys.clear()

Upvotes: 0

Related Questions