Getting an error

[aditi2709-03]

In the Predictions code for neural network I am getting an error for the following code:

pred = model.predict_classes(test_scale)
pred

AttributeError Traceback (most recent call last)
Input In [78], in <cell line: 1>()
----> 1 pred = model.predict_classes(test_scale)
2 pred

AttributeError: 'Sequential' object has no attribute 'predict_classes'

I tried replacing the first line of code with

pred = model.predict(test_scale)

but then I get the following error:

ValueError Traceback (most recent call last)
Input In [79], in <cell line: 1>()
----> 1 pred = model.predict(test_scale)
2 pred

File ~\anaconda3\lib\site-packages\keras\utils\traceback_utils.py:70, in filter_traceback..error_handler(*args, **kwargs)
67 filtered_tb = _process_traceback_frames(e.traceback)
68 # To get the full stack trace, call:
69 # tf.debugging.disable_traceback_filtering()
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb

File ~\AppData\Local\Temp_autograph_generated_filew1kbawns.py:15, in outer_factory..inner_factory..tf__predict_function(iterator)
13 try:
14 do_return = True
---> 15 retval = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
16 except:
17 do_return = False

ValueError: in user code:

File "C:\Users\Aditi\anaconda3\lib\site-packages\keras\engine\training.py", line 2041, in predict_function  *
    return step_function(self, iterator)
File "C:\Users\Aditi\anaconda3\lib\site-packages\keras\engine\training.py", line 2027, in step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\Aditi\anaconda3\lib\site-packages\keras\engine\training.py", line 2015, in run_step  **
    outputs = model.predict_step(data)
File "C:\Users\Aditi\anaconda3\lib\site-packages\keras\engine\training.py", line 1983, in predict_step
    return self(x, training=False)
File "C:\Users\Aditi\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
File "C:\Users\Aditi\anaconda3\lib\site-packages\keras\engine\input_spec.py", line 295, in assert_input_compatibility
    raise ValueError(

ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 254750, 20), found shape=(None, 20)

Please help me

[Kamalparanth]

is the issue resolved?

[aditi2709-03]

No I'm still getting the same error.
I tried the solutions from google but I get some other error 🤦🏻‍♀️

[benbluhm]

The example isn't using batches but TensorFlow expects batch size in first parameter. There are a few ways to achieve the same result. You could remove the shape for the input layer and either run model.summary() after training on data or after running a model.build(input_shape = (254750, 20)). You could also do a shape of (None,20) in the first layer but expect some warnings when training occurs.
I like this way of defining the input shape:

model = Sequential()
model.add(tf.keras.Input(shape=(20,)))
model.add(Dense(64, activation='relu')) 
model.add(Dense(128, activation='relu'))
model.add(Dense(256, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dense(11, activation='softmax'))

[Maheshwari241]

callbacks = [tf.keras.callbacks.TensorBoard("logs_keras")]
model.fit(X_train, a, epochs=20, callbacks=callbacks, validation_split = 0.2)
I'm getting error this