이미지 학습 강의중 두번째 강의

두번째 강의를 따라 하고 실행시켰을때 결과가 똑같이 나오기는 하는데 추가로 

Epoch 1/5
Traceback (most recent call last):
  File "C:\Users108\Desktop\deep\deep learning\fash.py", line 23, in <module>
    model.fit(trainX, trainY, epochs=5)
  File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "C:\Users108\AppData\Local\Temp\__autograph_generated_filets6yickf.py", line 15, in tf__train_function   
    retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)        
ValueError: in user code:

    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 
1051, in train_function  *
        return step_function(self, iterator)
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 
1040, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 
1030, in run_step  **
        outputs = model.train_step(data)
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 
890, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 
948, in compute_loss
        return self.compiled_loss(
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\compile_utils.py", 
line 201, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\losses.py", line 139, in __call__
        losses = call_fn(y_true, y_pred)
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\losses.py", line 243, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\losses.py", line 1787, in 
categorical_crossentropy
        return backend.categorical_crossentropy(
    File "C:\Users108\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\backend.py", line 5119, in categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)

ValueError: Shapes (32, 1) and (32, 10) are incompatible

이런 에러가 나오는데 왜 그런건가요

import tensorflow as tf 
import matplotlib.pyplot as plt

(trainX, trainY),(testX, testY)  = tf.keras.datasets.fashion_mnist.load_data()

# print(trainX)
# print(trainY)

class_name = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankleboot'
]

model = tf.keras.Sequential([
    tf.keras.layers.Dense(128, input_shape=(28,28), activation="relu"),
    tf.keras.layers.Dense(64, activation="relu"),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(10, activation="softmax"),
    
])

model.summary()

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(trainX, trainY, epochs=5)

똑같이 따라했습니다.