Autokeras: Customized Model example is not running

[ikscapes]

Bug Description

Customized Model example (Implement New Block) is not working.

Reproducing Steps

Steps to reproduce the behavior:

• Step 1: Change error line -> solved
  import autokeras as ak
  import tensorflow as tf

class SingleDenseLayerBlock(ak.Block):

def build(self, hp, inputs=None):
    # Get the input_node from inputs.
    input_node = tf.python.util.nest.flatten(inputs)[0] -> tf.nest.flatten(inputs)[0]
    layer = tf.keras.layers.Dense(
        hp.Int('num_units', min_value=32, max_value=512, step=32))
    output_node = layer(input_node)
    return output_node

• Step 2: Execute code -> training the model was performed, but an error occurred in the evaluation line.

Build the AutoModel

input_node = ak.Input()
output_node = SingleDenseLayerBlock()(input_node)
output_node = ak.RegressionHead()(output_node)
auto_model = ak.AutoModel(input_node, output_node, max_trials=10)

Prepare Data

num_instances = 100
x_train = np.random.rand(num_instances, 20).astype(np.float32)
y_train = np.random.rand(num_instances, 1).astype(np.float32)
x_test = np.random.rand(num_instances, 20).astype(np.float32)
y_test = np.random.rand(num_instances, 1).astype(np.float32)

Train the model

auto_model.fit(x_train, y_train)
print(auto_model.evaluate(x_test, y_test)) -> error!

The full error log is shown below.
Traceback (most recent call last):
File "D:/Ikjoo/Tensorflow Projects/AutoML/autokeras_example.py", line 39, in
print(auto_model.evaluate(x_test, y_test))
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagesautokerasauto_model.py", line 366, in evaluate
return self.tuner.get_best_model().evaluate(x=dataset, kwargs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagesautokerasenginetuner.py", line 37, in get_best_model
model = super().get_best_models()[0]
File "C:ProgramDataAnaconda3envstensorflowlibsite-packageskerastunerenginetuner.py", line 231, in get_best_models
return super(Tuner, self).get_best_models(num_models)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packageskerastunerenginebase_tuner.py", line 238, in get_best_models
models = [self.load_model(trial) for trial in best_trials]
File "C:ProgramDataAnaconda3envstensorflowlibsite-packageskerastunerenginebase_tuner.py", line 238, in
models = [self.load_model(trial) for trial in best_trials]
File "C:ProgramDataAnaconda3envstensorflowlibsite-packageskerastunerenginetuner.py", line 157, in load_model
trial.trial_id, best_epoch))
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerasenginetraining.py", line 234, in load_weights
return super(Model, self).load_weights(filepath, by_name, skip_mismatch)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerasenginenetwork.py", line 1193, in load_weights
status = self._trackable_saver.restore(filepath)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingtrackingutil.py", line 1283, in restore
checkpoint=checkpoint, proto_id=0).restore(self._graph_view.root)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingtrackingbase.py", line 209, in restore
restore_ops = trackable._restore_from_checkpoint_position(self) # pylint: disable=protected-access
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingtrackingbase.py", line 908, in _restore_from_checkpoint_position
tensor_saveables, python_saveables))
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingtrackingutil.py", line 289, in restore_saveables
validated_saveables).restore(self.save_path_tensor)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingsavingfunctional_saver.py", line 255, in restore
restore_ops.update(saver.restore(file_prefix))
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingsavingfunctional_saver.py", line 102, in restore
restored_tensors, restored_shapes=None)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingsavingsaveable_object_util.py", line 116, in restore
self.handle_op, self._var_shape, restored_tensor)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonopsresource_variable_ops.py", line 297, in shape_safe_assign_variable_handle
shape.assert_is_compatible_with(value_tensor.shape)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonframeworktensor_shape.py", line 1110, in assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
**ValueError: Shapes (1,) and (32,) are incompatible

Expected Behavior

Please let me know how you can solve the error.
(E.g. there is a problem loading the model, etc.)

Setup Details

Include the details about the versions of:

• OS type and version: Windows 10 Professional
• Python: 3.6.10
• autokeras: 1.0.1
• scikit-learn: 0.22.1
• numpy: 1.18.1
• keras: 1.0.8 (Keras-Applications)
• scipy: 1.4.1
• tensorflow: 2.1.0
• pytorch: x

Additional context

[ikscapes]

I reinstalled tensorflow and autokeras and ran it again.

Another error occurred while executing the code.

The full error log is shown below.
2020-02-12 20:43:47.329690: W tensorflow/core/framework/op_kernel.cc:1655] OP_REQUIRES failed at save_restore_v2_ops.cc:220 : Unknown: Failed to rename: .auto_modeltrial_d052e73d00eb40d2f1a00d4a472a874ccheckpointsepoch_0checkpoint_temp_43c9929389a54f28958954228a55ace5/part-00001-of-00002.data-00000-of-00001 to: .auto_modeltrial_d052e73d00eb40d2f1a00d4a472a874ccheckpointsepoch_0checkpoint.data-00001-of-00002 : �׼����� �źεǾ����ϴ�.
; Input/output error
Traceback (most recent call last):
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonopsgen_io_ops.py", line 493, in merge_v2_checkpoints
"delete_old_dirs", delete_old_dirs)
tensorflow.python.eager.core._FallbackException: This function does not handle the case of the path where all inputs are not already EagerTensors.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:/joo/Tensorflow Projects/AutoML/autokeras_customized_model.py", line 38, in
auto_model.fit(x_train, y_train, epochs=300)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagesautokerasauto_model.py", line 250, in fit
kwargs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagesautokerasenginetuner.py", line 132, in search
super().search(callbacks=new_callbacks, *fit_kwargs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packageskerastunerenginebase_tuner.py", line 130, in search
self.run_trial(trial, *fit_args, *fit_kwargs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagesautokerasenginetuner.py", line 91, in run_trial
history = model.fit(x, fit_args, *copied_fit_kwargs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerasenginetraining.py", line 819, in fit
use_multiprocessing=use_multiprocessing)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerasenginetraining_v2.py", line 397, in fit
prefix='val_')
File "C:ProgramDataAnaconda3envstensorflowlibcontextlib.py", line 88, in __exit__
next(self.gen)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerasenginetraining_v2.py", line 771, in on_epoch
self.callbacks.on_epoch_end(epoch, epoch_logs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerascallbacks.py", line 302, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerascallbacks.py", line 992, in on_epoch_end
self._save_model(epoch=epoch, logs=logs)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerascallbacks.py", line 1027, in _save_model
self.model.save_weights(filepath, overwrite=True)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonkerasenginenetwork.py", line 1123, in save_weights
self._trackable_saver.save(filepath, session=session)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingtrackingutil.py", line 1168, in save
file_prefix=file_prefix_tensor, object_graph_tensor=object_graph_tensor)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingtrackingutil.py", line 1116, in _save_cached_when_graph_building
save_op = saver.save(file_prefix)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythontrainingsavingfunctional_saver.py", line 238, in save
sharded_prefixes, file_prefix, delete_old_dirs=True)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonopsgen_io_ops.py", line 499, in merge_v2_checkpoints
delete_old_dirs=delete_old_dirs, name=name, ctx=_ctx)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythonopsgen_io_ops.py", line 525, in merge_v2_checkpoints_eager_fallback
attrs=_attrs, ctx=ctx, name=name)
File "C:ProgramDataAnaconda3envstensorflowlibsite-packagestensorflow_corepythoneagerexecute.py", line 61, in quick_execute
num_outputs)
**UnicodeDecodeError: 'utf-8' codec can't decode byte 0xbe in position 288: invalid start byte

There seems to be a problem with storing the model.
Could you tell me where to fix it?

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[yoo817]

I have the same problem. Have you solved it yet?