should we use caer.train_val_split or sklearn.model_selection when splitting data on line 62?

[harryhancock]

@jasmcaus pls help!

import matplotlib.pyplot as plt
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.callbacks import LearningRateScheduler
from sklearn.model_selection import train_test_split

IMG_SIZE = (80,80)
@@ -58,9 +59,10 @@
labels = to_categorical(labels, len(characters))

Creating train and validation data

split_data = caer.train_val_split(featureSet, labels, val_ratio=.2)

this produces error:

InvalidArgumentError Traceback (most recent call last)
in
47 validation_data=(x_val,y_val),
48 validation_steps=len(y_val)//BATCH_SIZE,
---> 49 callbacks = callbacks_list)
50
51 characters

/opt/conda/lib/python3.7/site-packages/tensorflow/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_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
1098 _r=1):
1099 callbacks.on_train_batch_begin(step)
-> 1100 tmp_logs = self.train_function(iterator)
1101 if data_handler.should_sync:
1102 context.async_wait()

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in call(self, *args, **kwds)
826 tracing_count = self.experimental_get_tracing_count()
827 with trace.Trace(self._name) as tm:
--> 828 result = self._call(*args, **kwds)
829 compiler = "xla" if self._experimental_compile else "nonXla"
830 new_tracing_count = self.experimental_get_tracing_count()

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
886 # Lifting succeeded, so variables are initialized and we can run the
887 # stateless function.
--> 888 return self._stateless_fn(*args, **kwds)
889 else:
890 _, _, _, filtered_flat_args = \

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in call(self, *args, **kwargs)
2941 filtered_flat_args) = self._maybe_define_function(args, kwargs)
2942 return graph_function._call_flat(
-> 2943 filtered_flat_args, captured_inputs=graph_function.captured_inputs) # pylint: disable=protected-access
2944
2945 @Property

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1917 # No tape is watching; skip to running the function.
1918 return self._build_call_outputs(self._inference_function.call(
-> 1919 ctx, args, cancellation_manager=cancellation_manager))
1920 forward_backward = self._select_forward_and_backward_functions(
1921 args,

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in call(self, ctx, args, cancellation_manager)
558 inputs=args,
559 attrs=attrs,
--> 560 ctx=ctx)
561 else:
562 outputs = execute.execute_with_cancellation(

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
58 ctx.ensure_initialized()
59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
62 if name is not None:

InvalidArgumentError: Can not squeeze dim[2], expected a dimension of 1, got 10
[[node binary_crossentropy/remove_squeezable_dimensions/Squeeze (defined at :49) ]] [Op:__inference_train_function_35716]

Function call stack:
train_function

OR
split_data = train_test_split(featureSet, labels, val_ratio=.2)

[jasmcaus]

Use sklearn.model_selection.train_test_split(featureSet, labels, val_ratio=.2) instead of caer.train_val_split(). The latter function is deprecated in caer.

So instead of this syntax (which was used in the course):
x_train, x_val, y_train, y_val = caer.train_val_split(featureSet, labels, val_ratio=.2)
use
x_train, x_val, y_train, y_val = sklearn.model_selection.train_test_split(featureSet, labels, val_ratio=.2)

[locorez]

Hi guys,
I had the same error than @harryhancock
After I have changed the syntax from:
x_train, x_val, y_train, y_val = caer.train_val_split(featureSet, labels, val_ratio=.2)

to
x_train, x_val, y_train, y_val = sklearn.model_selection.train_test_split(featureSet, labels, test_size=.2)

It has worked.

Thank you!

[jasmcaus]

That's great to hear @locorez! How about you @harryhancock? Did changing the syntax work for you?