CODEWITHSUNDEEP
pythontensorflowtensortensorflow2
Vitor Bento
Vitor Bento

Reputation: 404

iterating over `tf.Tensor` is not allowed

I am trying to use this function into a @tf.function decorato:

h and h2 is a tensor with shape [3,3]

def fn(h,i):
    print(h[i])
    return h[i]

tensor = [fn(h,i) for i in tf.range(tf.cast(tf.shape(h)[0],tf.int32)) if  tf.reduce_all(tf.equal(h[i],h2[i])) ]
tf.print(tensor)

But i am getting this erro:

main_coat_rds.py:139 train_step  *
        pseudo_label_1,images_discard_rede1=predict_aug_images(rede_2,rede_1,img_rede1_aug_1,img_rede1_aug_2,img_rede1_aug_3,img_rede1_aug_4,img_rede1_aug_5,img_rede1_aug_6,img_rede1_aug_7,img_rede1_aug_8,images_discard_rede1,Correct_labels)
    /vitor/codigo_noise_label/codigo_rds/utils_loss_function.py:289 predict_aug_images  *
        pred_match = [get_value_labels(all_predics,i) for i in tf.range(tf.cast(tf.shape(all_predics)[0],tf.int32)) if  tf.reduce_all(tf.equal(all_predics[i],all_predics_aj[i])) ]
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:503 __iter__
        self._disallow_iteration()
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:496 _disallow_iteration
        self._disallow_when_autograph_enabled("iterating over `tf.Tensor`")
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:474 _disallow_when_autograph_enabled
        " indicate you are trying to use an unsupported feature.".format(task))

    OperatorNotAllowedInGraphError: iterating over `tf.Tensor` is not allowed: AutoGraph did convert this function. This might indicate you are trying to use an unsupported feature.

What is another way that i can do it ?

Upvotes: 0

Views: 697

Answers (1)

Lescurel
Lescurel

Reputation: 11631

Whenever you want to select some part of a Tensor based on a condition, a good option is to use a combination of tf.gather and tf.where.

Here, for example, to select the rows that are equal between h and h2, you can use:

tf.gather_nd(h, tf.where(tf.reduce_all(tf.equal(h, h2),axis=1)))

Upvotes: 1

Related Questions