CODEWITHSUNDEEP
tensorflowkeras
eike
eike

Reputation: 61

"object has no attribute '_name_scope'" errors in tensorflow/keras

I'm trying to construct a custom loss function in tensorflow 2:

import tensorflow as tf
from tensorflow import keras

class YOLOv2Loss(keras.losses.Loss):
    def __init__(self,anchor_boxes):
        ...

However, if I then compile and fit a model that uses this loss function

anchor_boxes = ... # load anchor boxes from file
model = ... # build model here
train_batches = # extract training batches from tensorflow DataSet
yolov2_loss = YOLOv2Loss(anchor_boxes)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.5E-4)
model.compile(loss=yolov2_loss,optimizer=optimizer)
model.fit(train_batches)

I get

AttributeError: 'YOLOv2Loss' object has no attribute '_name_scope'

(full traceback included below).

I have tried to re-install tensorflow and keras (as suggested in some other posts) but none of this seems to fix the issue. I'm currently using tensorflow/keras version 2.8.0, i.e. the latest stable release.

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-2-6e793fdad18a> in <module>
     12 optimizer = tf.keras.optimizers.Adam(learning_rate=0.5E-4,beta_1=0.9,beta_2=0.999, epsilon=1.E-8, decay=0.0)
     13 model.compile(loss=yolov2_loss,optimizer=optimizer)
---> 14 model.fit(train_batches)

/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py in error_handler(*args, **kwargs)
     65     except Exception as e:  # pylint: disable=broad-except
     66       filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67       raise e.with_traceback(filtered_tb) from None
     68     finally:
     69       del filtered_tb

/usr/local/lib/python3.8/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
   1145           except Exception as e:  # pylint:disable=broad-except
   1146             if hasattr(e, "ag_error_metadata"):
-> 1147               raise e.ag_error_metadata.to_exception(e)
   1148             else:
   1149               raise

AttributeError: in user code:

    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1010, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1000, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 860, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 918, in compute_loss
        return self.compiled_loss(
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/compile_utils.py", line 201, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "/usr/local/lib/python3.8/dist-packages/keras/losses.py", line 136, in __call__
        with backend.name_scope(self._name_scope), graph_ctx:

    AttributeError: 'YOLOv2Loss' object has no attribute '_name_scope'

Upvotes: 2

Views: 822

Answers (2)

Samrat Thapa
Samrat Thapa

Reputation: 11

Adding the following line to the init function worked for me.

super().__init__(name="custom_loss",**kwargs)

Upvotes: 0

eike
eike

Reputation: 61

I figured it out, it has nothing to do with my tensorflow installation: looking at the keras source code, the attribute _name_scope is set in the constructor of the base class keras.losses.Loss and I had forgotten to call the parent constructor in my derived class.

Once I add

super().__init__()

to the constructor of my YOLOv2Loss class the problem disappears.

Upvotes: 4

Related Questions