InvalidArgumentError with Keras ImagedataGenerator

[andreaskopp]

Is there any guidance how to choose parameters in conjunction with the Keras ImagedataGenerator?

I experience InvalidArgumentError during the last quarter of the 1st epoch. I guess the issue is related to the combination of the following parameters:

• training samples: 10057
• batch size of train_generator / valididation_generator: 32 / 32
• step_size_train: 314
• step_size_valid: 126
• num_microbatches: 16

---

InvalidArgumentError Traceback (most recent call last) in 5 callbacks=[], 6 validation_data = validation_generator, ----> 7 validation_steps = step_size_valid)

/anaconda/envs/azureml_py36/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs) 725 max_queue_size=max_queue_size, 726 workers=workers, --> 727 use_multiprocessing=use_multiprocessing) 728 729 def evaluate(self,

/anaconda/envs/azureml_py36/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_generator.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing) 601 shuffle=shuffle, 602 initial_epoch=initial_epoch, --> 603 steps_name='steps_per_epoch') 604 605 def evaluate(self,

/anaconda/envs/azureml_py36/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_generator.py in model_iteration(model, data, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch, mode, batch_size, steps_name, **kwargs) 263 264 is_deferred = not model._is_compiled --> 265 batch_outs = batch_function(*batch_data) 266 if not isinstance(batch_outs, list): 267 batch_outs = [batch_outs]

/anaconda/envs/azureml_py36/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics) 1015 self._update_sample_weight_modes(sample_weights=sample_weights) 1016 self._make_train_function() -> 1017 outputs = self.train_function(ins) # pylint: disable=not-callable 1018 1019 if reset_metrics:

/anaconda/envs/azureml_py36/lib/python3.6/site-packages/tensorflow_core/python/keras/backend.py in call(self, inputs) 3474 3475 fetched = self._callable_fn(*array_vals, -> 3476 run_metadata=self.run_metadata) 3477 self._call_fetch_callbacks(fetched[-len(self._fetches):]) 3478 output_structure = nest.pack_sequence_as(

/anaconda/envs/azureml_py36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py in call(self, *args, **kwargs) 1470 ret = tf_session.TF_SessionRunCallable(self._session._session, 1471 self._handle, args, -> 1472 run_metadata_ptr) 1473 if run_metadata: 1474 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: Input to reshape is a tensor with 9 values, but the requested shape requires a multiple of 8 [[{{node training_12/Reshape}}]] [[metrics_12/acc/Identity/_1029]] (1) Invalid argument: Input to reshape is a tensor with 9 values, but the requested shape requires a multiple of 8 [[{{node training_12/Reshape}}]] 0 successful operations. 0 derived errors ignored.