TF one hot encode tensor object - tensorflow

Question

Running a simple logistic regression following the mnist simple example
my code:
x = np.array(xHotdog + xNotHotdog)
y = np.array(yHotdog + yNotHotdog)
print("y shape before: "+str(y.shape))
y = tf.one_hot(indices=y, depth=2)
print("y shape after: "+str(y.shape))
y.eval()
return x,y
Later I run:
sess.run([optimizer, cost], feed_dict={x: batch_xs,y: batch_ys})
Getting the error:
TypeError: The value of a feed cannot be a tf.Tensor object.
Acceptable feed values include Python scalars, strings, lists, numpy
ndarrays, or TensorHandles.For reference, the tensor obje ct was
Tensor("one_hot:0", shape=(6457, 2), dtype=float32) which was passed
to the feed with key Tensor("Placeholder_1:0", shape=(?, 2),
dtype=float32).

Answer 1

You want to pass Tensor object to feed_dict and it raise an error. As mentioned in docs:
The optional feed_dict argument allows the caller to override the
value of tensors in the graph.
feed_dict: A dictionary that maps graph elements to values
So you need some values for the feed_dict. As shown in the error:
Acceptable feed values include Python scalars, strings, lists, numpy
ndarrays, or TensorHandles
Option 1: In your case you pass Tensor object which cause such exception. The issue can resolve in this way:
y = tf.placeholder(tf.float32, [None, 10], name="Y")
y = tf.one_hot(indices=y, depth=2)
...
sess.run([optimizer, cost], feed_dict={x: batch_xs,y: batch_ys})
Option 2: You can also evaluate the value with (in this case feed_dict not needed):
a = np.random.randint(1, 10, [20])
b = tf.one_hot(a, depth=10)
with tf.Session() as sess:
print(a)
print(sess.run([b]))