Composed encoding circuits cannot be used in GridSearchCV

[rupof]

Composing (+) two encoding circuits and using them in GridSearchCV, returns an error.

See minimal example below:

from sklearn.datasets import make_moons
from sklearn.model_selection import train_test_split

from squlearn.kernel import ProjectedQuantumKernel, QSVC
from squlearn.util import Executor

from sklearn.model_selection import GridSearchCV
from squlearn.encoding_circuit import (
     HighDimEncodingCircuit)

X, y = make_moons(
    n_samples=100, random_state=0)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=0)

X_train = X_train[:,0]
X_test = X_test[:,0]

layered_ec = HighDimEncodingCircuit(num_qubits=1,num_features=1)  +  HighDimEncodingCircuit(num_qubits=1,num_features=1) 
pqk = ProjectedQuantumKernel(
    encoding_circuit=layered_ec,
    executor=Executor("pennylane", shots=5000))

qsvc = QSVC(quantum_kernel=pqk)
param_grid = {"num_qubits": [1,2],}
grid_search = GridSearchCV(qsvc, param_grid, cv=5)
grid_search.fit(X_train, y_train)