CODEWITHSUNDEEP
pythontensorflowmachine-learningkerasscikit-learn
Andrei Călugăr
Andrei Călugăr

Reputation: 145

Scikit-learn cross_val_score throws ValueError: The first argument to `Layer.call` must always be passed

I'm working on a deep learning project and I tried following a tutorial to evaluate my model with Cross-Validation.

I was looking at this tutorial: https://machinelearningmastery.com/use-keras-deep-learning-models-scikit-learn-python/

I started by first splitting my dataset into features and labels:

labels = dataset['Label']
features = dataset.loc[:, dataset.columns != 'Label'].astype('float64')

I have the following shapes:

features.shape ,labels.shape
((2425727, 78), (2425727,))

I used RobustScalar to scale my data and how I have

features
array([[ 1.40474359e+02, -1.08800488e-02,  0.00000000e+00, ...,
         0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
       [ 1.40958974e+02, -1.08609909e-02, -2.50000000e-01, ...,
         0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
       [ 1.40961538e+02, -1.08712390e-02, -2.50000000e-01, ...,
         0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
       ...,
       [ 1.48589744e+02, -1.08658453e-02,  0.00000000e+00, ...,
         0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
       [-6.92307692e-02,  1.77654485e-01,  1.00000000e+00, ...,
         0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
       [-6.92307692e-02,  6.18858398e-03,  5.00000000e-01, ...,
         0.00000000e+00,  0.00000000e+00,  0.00000000e+00]])

labels
array([0, 0, 0, ..., 0, 0, 0])

Now the data is ready to perform cross-validation.

from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import cross_val_score

# Function to create model, required for KerasClassifier
def create_model():
    # create model
    model= Sequential()
    model.add(Dense(128, activation='relu',input_shape = (78,1)))
    model.add(Dropout(0.01))
    model.add(Dense(15, activation='softmax'))

    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

#fix random seed for reproducibility
seed = 7
np.random.seed(seed)
kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=seed)

# create model
model = KerasClassifier(build_fn=create_model(), epochs=30, batch_size=64, verbose=0)

# evaluate using 5-fold cross-validation
results = cross_val_score(model, features, labels, cv=kfold,scoring='accuracy', error_score="raise")
print(results.mean())

After doing this I get this error thrown: "ValueError: The first argument to Layer.call must always be passed. "

I also check scikit learn documentation to check if I'm doing something wrong: https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.cross_val_score.html

I also tried to look tryed looking for others that could have had this issue such as: https://github.com/scikit-learn/scikit-learn/issues/18944

But I couldn't manage to fix this. Can someone help me with this please ?

Upvotes: 0

Views: 694

Answers (1)

tnte
tnte

Reputation: 113

model = KerasClassifier(build_fn=create_model(), ...)

Try removing the braces of function create_model since the Argument expects a callback function which will be called when needed. So it will be

model = KerasClassifier(build_fn=create_model, ... )

Upvotes: 2

Related Questions