I am getting Attribute Error, please help me.

[amitjaisr]

AttributeError Traceback (most recent call last)
in ()
106 random_labels = to_categorical(random_labels, 6)
107
--> 108 g_loss = adversarial_model.train_on_batch([z_noise2, random_labels], [1] * batch_size)
109
110 print("g_loss:{}".format(g_loss))

3 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics, return_dict)
1723 iterator = data_adapter.single_batch_iterator(self.distribute_strategy, x,
1724 y, sample_weight,
-> 1725 class_weight)
1726 self.train_function = self.make_train_function()
1727 logs = self.train_function(iterator)

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py in single_batch_iterator(strategy, x, y, sample_weight, class_weight)
1511 data = (x, y, sample_weight)
1512
-> 1513 _check_data_cardinality(data)
1514 dataset = dataset_ops.DatasetV2.from_tensors(data)
1515 if class_weight:

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py in _check_data_cardinality(data)
1520
1521 def _check_data_cardinality(data):
-> 1522 num_samples = set(int(i.shape[0]) for i in nest.flatten(data))
1523 if len(num_samples) > 1:
1524 msg = "Data cardinality is ambiguous:\n"

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py in (.0)
1520
1521 def _check_data_cardinality(data):
-> 1522 num_samples = set(int(i.shape[0]) for i in nest.flatten(data))
1523 if len(num_samples) > 1:
1524 msg = "Data cardinality is ambiguous:\n"

AttributeError: 'int' object has no attribute 'shape'

[amitjaisr]

Please look into this and help me, I am stuck here.
Also If you want I can share my whole code.

[kailashahirwar]

Check the type of data before you flatten it. There is a problem with your dataset.

[193947]

g_loss = adversarial_model.train_on_batch([z_noise2, random_labels], [1] * batch_size)
modify：
g_loss = adversarial_model.train_on_batch([z_noise2, random_labels], np.array([1] * batch_size).reshape(batch_size,1))