error in fit model function for relu activation

Question

I tried but getting this error:

Epoch 1/5
Traceback (most recent call last):
  File "d:\University\Sem6\CV\project\project.py", line 580, in <module>
    model.fit(train_augmented, steps_per_epoch=train_steps, validation_data=val_augmented, validation_steps=valid_steps, epochs=epochs)
  File "D:\University\Sem6\CV\project\myenv\Lib\site-packages\keras\src\utils\traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "D:\University\Sem6\CV\project\myenv\Lib\site-packages\tensorflow\python\eager\execute.py", line 53, in quick_execute
    tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
tensorflow.python.framework.errors_impl.InvalidArgumentError: Graph execution error:
Detected at node inception_v1/dense_3/Relu defined at (most recent call last):
  File "d:\University\Sem6\CV\project\project.py", line 580, in <module>
Matrix size-incompatible: In[0]: [32,2048], In[1]: [512,1024]
         [[{{node inception_v1/dense_3/Relu}}]] [Op:__inference_train_function_16627]

my code:

batch_size = 32  #  adjust this according to your system's capabilities
train_steps = len(train_images) 
valid_steps = len(val_images) 
model.fit(train_augmented, steps_per_epoch=train_steps, validation_data=val_augmented, validation_steps=valid_steps, epochs=epochs)

how can I solve this error?