python : Input 0 of layer "conv2d" is incompatible with the layer: expected axis -1 of input shape to have value 1, but received (None, 200, 200, 3)

Question

i am working in a Deep Learning Project using CNN but i am still a beginner & i have a proplem when trying to use the model to predict from an image file

the error : Input 0 of layer "conv2d" is incompatible with the layer: expected axis -1 of input shape to have value 1, but received (None, 200, 200, 3)

model :

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, Flatten, MaxPool2D, Dense
import matplotlib.pyplot as plt

import numpy as np
from sklearn.metrics import confusion_matrix
from sklearn.metrics import precision_recall_fscore_support
import seaborn as sns
import keras

import splitfolders

splitfolders.ratio(
    "input/Data/Data",
    output="./dataset",
    seed=7,
    ratio=(0.90, 0.050, 0.050)
)

train_datagen = ImageDataGenerator(rescale=1 / 255)
valid_datagen = ImageDataGenerator(rescale=1 / 255)
test_datagen = ImageDataGenerator(rescale=1 / 255)

train_dataset = train_datagen.flow_from_directory('./dataset/train',
                                                  target_size=(200, 200),
                                                  color_mode='grayscale',
                                                  class_mode='categorical',
                                                  batch_size=100,
                                                  )

test_dataset = test_datagen.flow_from_directory('./dataset/test',
                                                target_size=(200, 200),
                                                class_mode='categorical',
                                                color_mode='grayscale',
                                                batch_size=100,
                                                shuffle=False
                                                )

valid_dataset = valid_datagen.flow_from_directory('./dataset/val',
                                                  target_size=(200, 200),
                                                  class_mode='categorical',
                                                  batch_size=100,
                                                  color_mode='grayscale',
                                                  )

model = Sequential()

model.add(Conv2D(32, (3, 3), activation='relu', input_shape=train_dataset.image_shape))
model.add(MaxPool2D(2))

model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPool2D(2))

model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPool2D(2))

model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPool2D(2))

model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPool2D(2))

model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPool2D(2))

model.add(Flatten())

model.add(Dense(512, activation='relu'))

model.add(Dense(4, activation='softmax'))

model.summary()


METRICS = [
    'accuracy',
    keras.metrics.Precision(name='precision'),
    keras.metrics.Recall(name='recall')
]

model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=METRICS)

Info = model.fit(
    train_dataset,
    validation_data=valid_dataset,
    epochs=5,
)

fig, ax = plt.subplots(1, 4, figsize=(20, 3))
ax = ax.ravel()

for i, met in enumerate(['precision', 'recall', 'accuracy', 'loss']):
    ax[i].plot(Info.history[met])
    ax[i].plot(Info.history['val_' + met])
    ax[i].set_title('Model {}'.format(met))
    ax[i].set_xlabel('epochs')
    ax[i].set_ylabel(met)
    ax[i].legend(['train', 'val'])

predictions = model.predict(test_dataset)

diseases_labels = []

for key, value in train_dataset.class_indices.items():
    diseases_labels.append(key)


    def evaluate(actual, predictions):
        pre = []
        for i in predictions:
            pre.append(np.argmax(i))

        accuracy = (pre == actual).sum() / actual.shape[0]
        print(f'Accuracy: {accuracy}')

        precision, recall, f1_score, _ = precision_recall_fscore_support(actual, pre, average='macro')
        print(f'Precision: {precision}')
        print(f'Recall: {recall}')
        print(f'F1_score: {f1_score}')

        fig, ax = plt.subplots(figsize=(20, 20))
        conf_mat = confusion_matrix(actual, pre)
        sns.heatmap(conf_mat, annot=True, fmt='.0f', cmap="YlGnBu", xticklabels=diseases_labels,
                    yticklabels=diseases_labels).set_title('Confusion Matrix Heat map')
        plt.show()

        evaluate(test_dataset.classes, predictions)

model.evaluate(test_dataset)
model.save('model/KidneyDiseasesModel.h5')

model_test :

from keras.models import load_model
from keras.preprocessing import image
import numpy as np

model = load_model('model/KidneyDiseasesModel.h5')

test_image = image.load_img('test.jpg', target_size=(200, 200, 1))
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis=0)

result = model.predict(test_image)

image to test : test image

Can anyone help me Please ?