Getting an Value Error from using the mean squared error loss function

[athenax246]

I am training a feed-forward neural network that takes in the input of shape (4040 ,2) and output of shape (4040, 4, 51).

I tried using the Panda data frame for it first, however, it does not seem to work with a 3-dimensional output shape. (If there is a way to covert 3-dimensional data into Panda data frame please let me know)

So for now I am using numpy array to store the inputs and outputs. But they are now the same shape, and will raise and error when going through the mean squared error loss function.

Any comments, solutions and suggestions are greatly appreciated!

---

The code I have is the following:

#using functional API
def build_model90():
    input_layer = Input(shape = repeated_norm_train_dime.shape)

    dense_1 = Dense(units='1024', activation='relu')(input_layer)
    dense_2 = Dense(units='512', activation='relu')(dense_1)

    y1_output = Dense(units='1', name='Tx_output')(dense_2)
    y2_output = Dense(units='1', name='Ty_output')(dense_2)
    y3_output = Dense(units='1', name='Px_output')(dense_2)
    y4_output = Dense(units='1', name='Py_output')(dense_2)

    # Define the model with the input layer and a list of output layers
    model = Model(inputs=input_layer, outputs=[y1_output, y2_output, y3_output, y4_output])
    return model

# Set random seed
tf.random.set_seed(27)

forward_90= build_model90()

# Specify the optimizer, and compile the model with loss functions for both outputs
#optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001)

optimizer="Adam"
forward_90.compile(optimizer=optimizer, loss={'Tx_output': 'mse', 'Ty_output': 'mse', 'Px_output': 'mse', 'Py_output': 'mse'})

# Train the model for 100 epochs
epochs = 100
history_90 = forward_90.fit(tf.expand_dims(repeated_norm_train_dime, axis = 0), tf.expand_dims(train_resp, axis = 0), 
                            epochs=epochs, batch_size=4040, validation_data=(norm_test_dime, test_resp))

---

The error that I got is the following:

ValueError                                Traceback (most recent call last)
[<ipython-input-81-5f285747b2b0>](https://localhost:8080/#) in <cell line: 3>()
      1 # Train the model for 100 epochs
      2 epochs = 100
----> 3 history_90 = forward_90.fit(tf.expand_dims(repeated_norm_train_dime, axis = 0), tf.expand_dims(train_resp, axis = 0), 
      4                             epochs=epochs, batch_size=4040, validation_data=(norm_test_dime, test_resp)) #add: callbacks=[lr_scheduler]

1 frames
[/usr/local/lib/python3.10/dist-packages/keras/engine/training.py](https://localhost:8080/#) in tf__train_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 "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1284, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1268, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1249, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1051, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1109, in compute_loss
        return self.compiled_loss(
    File "/usr/local/lib/python3.10/dist-packages/keras/engine/compile_utils.py", line 265, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "/usr/local/lib/python3.10/dist-packages/keras/losses.py", line 142, in __call__
        losses = call_fn(y_true, y_pred)
    File "/usr/local/lib/python3.10/dist-packages/keras/losses.py", line 268, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "/usr/local/lib/python3.10/dist-packages/keras/losses.py", line 1470, in mean_squared_error
        return backend.mean(tf.math.squared_difference(y_pred, y_true), axis=-1)

    ValueError: Dimensions must be equal, but are 2 and 4 for '{{node mean_squared_error/SquaredDifference}} = SquaredDifference[T=DT_FLOAT](model_6/Tx_output/BiasAdd, Cast)' with input shapes: [?,4040,2,1], [?,4040,4,51].

I need some advice with how to process multi-dimensional data (with different input and output shapes) with tensorflow in general. Because before this I was mostly relying on pd.dataframe, but now it does not seem to work for this situation. Thanks!

[Sakthi-Developer]

Increas the axis of the fiting data .

[Sakthi-Developer]

Or decrease the Axis less then zero