CODEWITHSUNDEEP
pythontensorflow
Jon.W
Jon.W

Reputation: 129

TypeError when feeding tensorflow placeholder

I am trying to feed a placeholder with following statements:

image = tf.placeholder(tf.int32,shape = (256,256))
image.eval(feed_dict={image, (image_)})

where image_ is:

array([[ 5, 12,  8, ..., 21,  2, 11],
       [ 5, 11, 13, ...,  9, 12,  4],
       [ 7,  2, 13, ...,  7,  9,  6],
       ..., 
       [ 1,  1,  6, ...,  8,  2,  4],
       [ 0,  2,  6, ...,  3,  6,  7],
       [ 4,  1,  4, ...,  9,  0,  5]], dtype=uint32)

And I am getting the error that:TypeError: unhashable type: 'numpy.ndarray'. Anyone has any ideas?

BTW, I am trying to load .mat file into tensor as images. Do i have better options?

Thanks.

Upvotes: 0

Views: 116

Answers (1)

Miriam Farber
Miriam Farber

Reputation: 19634

feed_dict should be a dictionary, so you need to change the line

image.eval(feed_dict={image, (image_)})

into

image.eval(feed_dict={image:image_})

Upvotes: 1

Related Questions