K-Fold Cross Validation is not working with perceptron?

Question

I was working on a simple perceptron model and k-fold cross-validation. Then I found that the k-fold cross-validation does not work on this model. I tried different approaches from scikit-learn such as cross_val_score, cross_val_predict, and cross_validate

class Perceptron(tf.keras.Model):
    def __init__(self):
        super(Perceptron, self).__init__()
        self.dense = tf.keras.layers.Dense(units=1, activation='sigmoid')

    def call(self, inputs):
        return self.dense(inputs)

model = Perceptron()
model.compile(optimizer='sgd', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=100, batch_size=1)

kfold = KFold(n_splits=5, shuffle=True, random_state=42)

scores = cross_val_predict(model, x_train, y_train, cv=5)
# print("fit scores: {}".format(scores['test_score']))

# # Perform k-fold cross-validation and calculate the precision, recall, and F1-score
# perceptron_scores = cross_val_score(Perceptron(), x_train, y_train, cv=kfold, scoring='accuracy')

Here is the error message:

Empty                                     Traceback (most recent call last)
File ~/miniconda3/envs/tensorflow/lib/python3.10/site-packages/joblib/parallel.py:862, in Parallel.dispatch_one_batch(self, iterator)
    861 try:
--> 862     tasks = self._ready_batches.get(block=False)
    863 except queue.Empty:
    864     # slice the iterator n_jobs * batchsize items at a time. If the
    865     # slice returns less than that, then the current batchsize puts
   (...)
    868     # accordingly to distribute evenly the last items between all
    869     # workers.

File ~/miniconda3/envs/tensorflow/lib/python3.10/queue.py:168, in Queue.get(self, block, timeout)
    167     if not self._qsize():
--> 168         raise Empty
    169 elif timeout is None:

Empty: 

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
/home/jinzzasol/Code/cs5834/assignment4/hw4.ipynb Cell 38 line 4
      1 # Define the cross-validation object
      2 kfold = KFold(n_splits=5, shuffle=True, random_state=42)
...
    102             )
    104 klass = estimator.__class__
    105 new_object_params = estimator.get_params(deep=False)

TypeError: Cannot clone object '<__main__.Perceptron object at 0x7fa9c85aa5f0>' (type <class '__main__.Perceptron'>): it does not seem to be a scikit-learn estimator as it does not implement a 'get_params' method.