i am fine-tuning and training Xception model. then saving model using model.save(). After loding the model using model.load_model(), i am getting this error “Input 0 of layer “dense_1″ is incompatible with the layer: expected min_ndim=2, found ndim=1. Full shape received: (128,)”.

If i dont save model and make predictions just after the training, then it is working perfect. But issue arises after saving and then loading the model to make predictions. Please help me where i am doing wrong

base_model =keras.applications.Xception(input_shape=(256, 256, 3), include_top=False, weights='imagenet',
                                        pooling= 'max')

model = Sequential([
base_model,
Dropout(0.5),
Dense(128, activation='relu'),
Dropout(0.25),
Dense(4, activation='softmax')

])
model.compile(optimizer=’adam’, loss=’categorical_crossentropy’, metrics=[‘accuracy’])

lr_reducer = ReduceLROnPlateau(factor=np.sqrt(0.1),
                           cooldown=0,
                           patience=5,
                           min_lr=0.5e-6)
checkpoint = ModelCheckpoint(filepath='//content/gdrive/MyDrive/xception2FE1_adam_LR_Norm_10epoch.keras',
                           verbose=1, save_best_only=True)

early = EarlyStopping(monitor='val_loss', min_delta=0, patience=8,  verbose=1, mode='auto')
history = model.fit(train_ds,
                epochs = 10, verbose=1,
                validation_data = valid_ds, callbacks=[lr_reducer, checkpoint, early])
model.save('/content/gdrive/MyDrive/XceptionFeatExtr_LR_NORM_10.keras')
print('model is saved')
new_model = tensorflow.keras.models.load_model('/content/gdrive/MyDrive/XceptionFeatExtr_LR_NORM_10.keras')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-13-9165482b3bac> in <cell line: 1>()
----> 1 new_model = tensorflow.keras.models.load_model('/content/gdrive/MyDrive/XceptionFeatExtr_LR_NORM_10.keras')
      2 print(new_model.summary())

11 frames
/usr/local/lib/python3.10/dist-packages/keras/src/layers/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    200         if spec.min_ndim is not None:
    201             if ndim is not None and ndim < spec.min_ndim:
--> 202                 raise ValueError(
    203                     f'Input {input_index} of layer "{layer_name}" '
    204                     "is incompatible with the layer: "

ValueError: Input 0 of layer "dense_1" is incompatible with the layer: expected min_ndim=2, found ndim=1. Full shape received: (128,)