On Neural Network algorithm trained with 10-fold CV on BNP Paribas dataset I got an error:
2020-07-24 08:57:26,104 supervised.exceptions ERROR Cannot load AutoML directory. Shapes (232, 32) and (231, 32) are incompatible
Traceback (most recent call last):
File "/home/piotr/sandbox/mljar-supervised/supervised/automl.py", line 385, in load
m = ModelFramework.load(model_path)
File "/home/piotr/sandbox/mljar-supervised/supervised/model_framework.py", line 389, in load
l = AlgorithmFactory.load(learner_desc, learner_path)
File "/home/piotr/sandbox/mljar-supervised/supervised/algorithms/factory.py", line 26, in load
learner.load(model_file_path)
File "/home/piotr/sandbox/mljar-supervised/supervised/algorithms/nn.py", line 181, in load
self.model.load_weights(model_file_path)
File "/home/piotr/sandbox/mljar-supervised/venv_mljs/lib/python3.6/site-packages/keras/engine/saving.py", line 492, in load_wrapper
return load_function(*args, **kwargs)
File "/home/piotr/sandbox/mljar-supervised/venv_mljs/lib/python3.6/site-packages/keras/engine/network.py", line 1230, in load_weights
f, self.layers, reshape=reshape)
File "/home/piotr/sandbox/mljar-supervised/venv_mljs/lib/python3.6/site-packages/keras/engine/saving.py", line 1237, in load_weights_from_hdf5_group
K.batch_set_value(weight_value_tuples)
File "/home/piotr/sandbox/mljar-supervised/venv_mljs/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2960, in batch_set_value
tf_keras_backend.batch_set_value(tuples)
File "/home/piotr/sandbox/mljar-supervised/venv_mljs/lib/python3.6/site-packages/tensorflow/python/keras/backend.py", line 3384, in batch_set_value
x.assign(np.asarray(value, dtype=dtype(x)))
File "/home/piotr/sandbox/mljar-supervised/venv_mljs/lib/python3.6/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 846, in assign
self._shape.assert_is_compatible_with(value_tensor.shape)
File "/home/piotr/sandbox/mljar-supervised/venv_mljs/lib/python3.6/site-packages/tensorflow/python/framework/tensor_shape.py", line 1117, in assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (232, 32) and (231, 32) are incompatible
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "examples/scripts/binary_classifier_BNP_GoldenFeatures.py", line 17, in <module>
automl = AutoML(results_path="/media/piotr/2t/kaggle/bnp_paribas/AutoML_Compete_v24", mode="Compete", total_time_limit=24*60*60)
File "/home/piotr/sandbox/mljar-supervised/supervised/automl.py", line 287, in __init__
self._set_results_dir()
File "/home/piotr/sandbox/mljar-supervised/supervised/automl.py", line 346, in _set_results_dir
self.load()
File "/home/piotr/sandbox/mljar-supervised/supervised/automl.py", line 403, in load
raise AutoMLException(f"Cannot load AutoML directory. {str(e)}")
supervised.exceptions.AutoMLException: Cannot load AutoML directory. Shapes (232, 32) and (231, 32) are incompatible
This might be because there are different size in categorical encoding between folds, but the framework should handle it.
On Neural Network algorithm trained with 10-fold CV on BNP Paribas dataset I got an error:
This might be because there are different size in categorical encoding between folds, but the framework should handle it.