Tensorflow Addons R2 ValueError：两个形状中的尺寸 0 必须相等，但 1 和 5

Question

I have been trying to add a tfa metric to my model compile to be tracked throughout the training. However, when I add the R2 metric, I get the following error. I thought y_shape=(1,) would fix this, however it did not.

    ValueError: Dimension 0 in both shapes must be equal, but are 1 and 5. Shapes are [1] and [5]. for '{{node AssignAddVariableOp_8}} = AssignAddVariableOp[dtype=DT_FLOAT](AssignAddVariableOp_8/resource, Sum_6)' with input shapes: [], [5].

My code is shown below:

    model = Sequential()
    model.add(Input(shape=(4,)))
    model.add(Normalization())
    model.add(Dense(5, activation="relu", kernel_regularizer=l2(l2=1e-2)))
    print(model.summary())

    opt = Adam(learning_rate = 1e-2)
    model.compile(loss="mean_squared_error", optimizer=tf.keras.optimizers.Adam(learning_rate=1e-2), metrics=[MeanSquaredError(name="mse"), MeanAbsoluteError(name="mae"), tfa.metrics.RSquare(name="R2", y_shape=(1,))])

    history = model.fit(x = training_x,
                        y = training_y,
                        epochs = 10,
                        batch_size = 64,
                        validation_data = (validation_x, validation_y)
                        )

Any help is greatly appreciated, Note, I also tried changing the y_shape to (5,), but then I get the error that the dimensions are not equal. but are 5 and 1...

Answer 1

You need to add an output layer to your model like the below:

model.add(Dense(1))

then your model will be like below:

model = Sequential()
model.add(Input(shape=(4,)))
model.add(Normalization())
model.add(Dense(5, activation="relu", kernel_regularizer=regularizers.l2(l2=1e-2)))
model.add(Dense(1))
print(model.summary())

Output:

Model: "sequential_10"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 normalization_10 (Normaliza  (None, 4)                9         
 tion)                                                           
                                                                 
 dense_12 (Dense)            (None, 5)                 25        
                                                                 
 dense_13 (Dense)            (None, 1)                 6         
                                                                 
=================================================================
Total params: 40
Trainable params: 31
Non-trainable params: 9