ValueError: Error when checking input: expected conv2d_1_input to have shape (216, 360, 3) but got array with shape (300, 500, 3)��#266

def dataAdv1():
    dfAll = pd.read_csv('filePath')
    labels = pd.read_csv('filePath')

    df = pd.read_csv('filePath')
    
    #this function returns a list of all the images
    imageList = createImageList(df, dfAll)
    imageTmp = imageList
    # this function is used to get the list of labels
    labels_list = clearAdvancingLabel(labels)
    labelTmp = labels_list
    #this function divide the data into train, validation and test set
    x_train, y_train, x_valid, y_valid, x_test, y_test = splitTrainValidationTest(imageTmp, labelTmp)
    
    y_train = y_train.ravel()
    y_valid = y_valid.ravel()
    y_test = y_test.ravel()
    
    return x_train, y_train, x_test, y_test, x_valid, y_valid


def create_modelAdvancing(x_train, y_train, x_test, y_test, x_valid, y_valid):
    model = Sequential()
    model.add(Conv2D({{choice([4, 16, 32, 64])}}, (3, 3), input_shape=(216, 360, 3)))
    model.add(Activation({{choice(['relu', 'tanh'])}}))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    
    num_layers = {{choice(['one', 'two', 'three', 'four'])}}
    
    if num_layers =='two':
        model.add(Conv2D({{choice([4, 16, 32, 64])}}, (3, 3)))
        model.add(Activation({{choice(['relu', 'tanh'])}}))
        model.add(MaxPooling2D(pool_size=(2, 2)))
    elif num_layers == 'three':
        model.add(Conv2D({{choice([4, 16, 32, 64])}}, (3, 3)))
        model.add(Activation({{choice(['relu', 'tanh'])}}))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Conv2D({{choice([4, 16, 32, 64])}}, (3, 3)))
        model.add(Activation({{choice(['relu', 'tanh'])}}))
        model.add(MaxPooling2D(pool_size=(2, 2)))
    elif num_layers == 'four':
        model.add(Conv2D({{choice([4, 16, 32, 64])}}, (3, 3)))
        model.add(Activation({{choice(['relu', 'tanh'])}}))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Conv2D({{choice([4, 16, 32, 64])}}, (3, 3)))
        model.add(Activation({{choice(['relu', 'tanh'])}}))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Conv2D({{choice([4, 16, 32, 64])}}, (3, 3)))
        model.add(Activation({{choice(['relu', 'tanh'])}}))
        model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Flatten())  
    model.add(Dense({{choice([4, 16, 32, 64])}}))
    model.add(Activation({{choice(['relu', 'tanh'])}}))
    model.add(Dropout({{uniform(0, 1)}}))
    model.add(Dense(1))
    model.add(Activation({{choice(['softmax', 'sigmoid'])}}))
    
    chooseOptimizer = {{choice(['adam', 'sgd', 'rmsprop'])}}    
    model.compile(loss='binary_crossentropy', optimizer=chooseOptimizer, metrics=['accuracy'])

    model.fit(x_train, y_train,
              batch_size={{choice([4, 16, 32, 64])}},
              epochs={{choice([10, 30, 50])}},
              verbose=2,
              validation_data=(x_valid, y_valid))
    score, acc = model.evaluate(x_test, y_test, verbose=0)
    print('Test accuracy:', acc)
    return {'loss': -acc, 'status': STATUS_OK, 'model': model.to_yaml()}


# Create Spark context
conf = SparkConf().setAppName('Elephas_Hyperparameter_Optimization').setMaster('local[*]')
sc = SparkContext(conf=conf)

# Define hyper-parameter model and run optimization
hyperparam_model = HyperParamModel(sc)
hyperparam_model.minimize(model=create_modelAdvancing, data=dataAdv1, max_evals=5)