ValueError: should I reshape the input layer

Question

This is the error I've got today which is,

ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 3072 but received input with shape [None, 32, 32, 3]

Here below is my code.

What is the best way to solve it? changing the last two liines or reshape im?

Thanks in advance.

import keras
from keras.datasets import cifar10
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.models import model_from_json
import os

num_classes = 10
im_rows = 32
im_cols = 32
im_size = im_rows *im_cols *3

(X_train, y_train),(X_test, y_test) = cifar10.load_data()
X_train = X_train.reshape(-1, im_size).astype('float32')/255
X_test = X_test.reshape(-1, im_size).astype('float32')/255

y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Dense(512, activation ='relu', input_shape=(im_size,)))
model.add(Dense(num_classes,activation='softmax'))

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

hist = model.fit(X_train, y_train,
                 batch_size=32, epochs=30,
                 verbose=1,
                 validation_data = (X_test, y_test))
model.summary()

score = model.evaluate(X_test, y_test, verbose =1)
print('accuracy=', score[1], 'loss=', score[0])

# serialize model to JSON
model_json = model.to_json()
with open("model.json", "w") as json_file:
    json_file.write(model_json)
# serialize weights to HDF5
model.save_weights("cifar10_mlp_weight.h5")
print("Saved model to disk")

json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights into new model
loaded_model.load_weights("cifar10_mlp_weight.h5")
print("Loaded model from disk")

im = cv2.imread('/Users/benno/Documents/Python/data/images/car.jpg')
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
im = cv2.resize(im, (32, 32))
plt.imshow(im) 
plt.show()

#This line shows error#
r = model.predict(np.array([im]), batch_size=32, verbose =1)
res = r[0]```