1

I want to count the number of matching label in a custom error function

I tested : 

def custom__error(y_true, y_pred):
  # ---- y_pred
  yp = tf.nn.softmax( y_pred)
  bp = tf.argsort(yp,axis=-1,direction='DESCENDING',stable=False,name=None)
  cp = tf.keras.backend.eval(bp)
  # ---- y_true
  yt = tf.nn.softmax( y_true )
  bt = tf.argsort(yt,axis=-1,direction='DESCENDING',stable=False,name=None)
  ct = tf.keras.backend.eval(bt)
  # ---- common
  count =  tf.sets.intersection(cp[None,:10],ct[None,:10])
  return count

but I got an error:

AttributeError: 'Tensor' object has no attribute '_numpy'

I also tried :

 def custom__error(y_true, y_pred):
  # ---- y_pred
  yp = tf.nn.softmax( y_pred)
  bp = tf.argsort(yp,axis=-1,direction='DESCENDING',stable=False,name=None)
  cp = bp.to_numpy()
  xcp = cp[None,:10]
  # ---- y_true
  yt = tf.nn.softmax( y_true )
  bt = tf.argsort(yt,axis=-1,direction='DESCENDING',stable=False,name=None)
  ct = bt.to_numpy()
  xct = ct[None,:10]
  # ---- common
  count =  tf.sets.intersection(tf.convert_to_tensor(xcp),tf.convert_to_tensor(xct))
  return count

I don't know how to use tf.sets.intersection inside tensorflow backend function.

Can someone help me understand ?

The complete error

AttributeError                            Traceback (most recent call last)
<ipython-input-319-eed924909205> in <module>()
      4 print(optimizer.learning_rate.numpy())  # or print(optimizer.lr.numpy())
      5 model_loss=custom__loss(100,100,1,0.01)
----> 6 model.compile(loss=model_loss, optimizer=optimizer, metrics=['accuracy',custom__error])

11 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py in <listcomp>(.0)
   3798     return nest.pack_sequence_as(
   3799         self._outputs_structure,
-> 3800         [x._numpy() for x in outputs],  # pylint: disable=protected-access
   3801         expand_composites=True)
   3802 

AttributeError: 'Tensor' object has no attribute '_numpy'

I tried to return numpy array :

return count.to_numpy()

or with:

def custom__error(y_true, y_pred):
  # ---- y_pred
  yp = tf.nn.softmax( y_pred)
  bp = tf.argsort(yp,axis=-1,direction='DESCENDING',stable=False,name=None)
  cp = bp.to_numpy()
  xcp = cp[None,:10]
  # ---- y_true
  yt = tf.nn.softmax( y_true )
  bt = tf.argsort(yt,axis=-1,direction='DESCENDING',stable=False,name=None)
  ct = bt.to_numpy()
  xct = ct[None,:10]
  # ---- common
  count =  tf.sets.intersection(xcp,xct)
  return count

but got the same error:

<ipython-input-114-59d27aab97e1> in custom__error(y_true, y_pred)
      3   yp = tf.nn.softmax( y_pred)
      4   bp = tf.argsort(yp,axis=-1,direction='DESCENDING',stable=False,name=None)
----> 5   cp = bp.to_numpy()
      6   xcp = cp[None,:10]
      7   # ---- y_true

AttributeError: 'Tensor' object has no attribute 'to_numpy'

<ipython-input-91-16ca4acce397> in custom__error(y_true, y_pred)
     12   # ---- common
     13   count =  tf.sets.intersection(xcp,xct)
---> 14   return count.numpy()
     15 
     16 

AttributeError: 'SparseTensor' object has no attribute 'numpy'
Improve this question
4
  • Please share the complete error message Commented May 17, 2020 at 12:32
  • @Kashinath Patekar Complete error message added Commented May 17, 2020 at 14:27
  • 1
    The title should be something like "AttributeError: 'Tensor' object has no attribute '_numpy' when using custom metrics function". That will help other users to find this question. I am proposing an edit. Commented May 18, 2020 at 5:22
  • Which version of tensorflow are you using? Commented May 18, 2020 at 17:16

1 Answer 1

Reset to default
1

In this line:

model.compile(loss=model_loss, optimizer=optimizer, metrics=['accuracy',custom__error])

the custom__error function is expected to return a numpy array, whereas tf.insersection would give you Tensor's in this case because y_true and y_pred passed to tf.intersection are tensors themselves.

Hence you would first need to convert count to a numpy array before returning it.

This answer might help.


Edit:
count is SparseTensor, hence first convert it to a dense tensor with:

dcount = tf.sparse.to_dense(count)

Then you need to check the mode in which tensorflow is running. You can it using this:

tf.executing_eagerly()
  • If this returns True:
    Eager mode active. You need to call .numpy() on the tensor to be converted.
  • If this returns False:
    Graph mode active. You need to call .eval() on the tensor to be converted.

If you like you can automate it for you:

if tf.executing_eagerly():
    return dcount.numpy()
else
    return dcount.eval()

Credit: TF 2.0 'Tensor' object has no attribute 'numpy' while using .numpy() although eager execution enabled by default


If you are using Tensorflow 1.x, you may need to enable eager execution manually. Check this answer for details.

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

8 Comments

I have updated the answer. The method .to_numpy() does not exist, hence the error. The error did change. It was as different place, and for different reason. I hope the updated answer solves the issue for you, cheers!
<ipython-input-91-16ca4acce397> in custom__error(y_true, y_pred) 12 # ---- common 13 count = tf.sets.intersection(xcp,xct) ---> 14 return count.numpy() 15 16 AttributeError: 'SparseTensor' object has no attribute 'numpy'
Thanks for your help : TensorFlow 2.x selected,but got SparseTensor' object has no attribute 'numpy'.
Then you would first need to convert the sparse tensor to dense tensor. (SparseTensor -> Tensor). A quick Google search should do the trick. To recap, original count (SparseTensor) => (dense) Tensor => numpy array
count = tf.sets.intersection(xcp,xct) dcount = tf.sparse.to_dense(count) return dcount.numpy()
|

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.