Type error during fitting

[nfurth]

When I fit the model, I received this error: TypeError: Expected int64 passed to parameter 'y' of op 'Maximum', got 1e-12 of type 'float' instead. Error: Expected int64, but got 1e-12 of type 'float'.
which can be traced back to the warning TypeError: not all arguments converted during string formatting during the train generator,
is there any fix for this?

Thank you

[Luca96]

Hi, without the full traceback is a little bit difficult to understand where the error is, could you provide it?

[nfurth]

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:13: UserWarning: Model.fit_generator is deprecated and will be removed in a future version. Please use Model.fit, which supports generators.
del sys.path[0]
Epoch 1/12

TypeError Traceback (most recent call last)
in ()
11 shuffle=True,
12 callbacks=[checkpoint],
---> 13 verbose=1
14 )

2 frames
/usr/local/lib/python3.7/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

TypeError: in user code:

File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function  *
    return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step  **
    outputs = model.train_step(data)
File "/usr/local/lib/python3.7/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/python3.7/dist-packages/keras/engine/training.py", line 919, in compute_loss
    y, y_pred, sample_weight, regularization_losses=self.losses)
File "/usr/local/lib/python3.7/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/python3.7/dist-packages/keras/losses.py", line 141, in __call__
    losses = call_fn(y_true, y_pred)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 245, in call  **
    return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 2199, in cosine_similarity
    y_true = tf.linalg.l2_normalize(y_true, axis=axis)

TypeError: Expected int64 passed to parameter 'y' of op 'Maximum', got 1e-12 of type 'float' instead. Error: Expected int64, but got 1e-12 of type 'float'.

Here are the library versions I am using:
OpenCV 4.1.2
Keras 2.8.0
Pandas 1.3.5
Numpy 1.21.5

If it helps a link to the notebook https://colab.research.google.com/drive/1eFgQqA6KC1acSCXbzc8ru5ffea5Oim7Q#scrollTo=dlfjYC2DrXhI

Thank you

[Luca96]

Hi, you can try a couple of things:

• Change the loss function to binary_crossentropy.
• And/or replace all the keras related imports with tensorflow.keras, instead.

Let me know if the issue persists