Can't figure out which input shape to build a keras model with

Question

I used keras_tuner to find the optimal hyperparameters for a model to analyze a specific dataset, but when I try to build the model to look at the output it requires an input shape. Every input shape I try returns an error, most often ValueError: In this 'tf.Variable' creation, the initial value's shape ((16, 320)) is not compatible with the explicitly supplied 'shape' argument ((784, 320)).

In the tutorial I followed, they said to use (None, 28, 28) as the input shape but inputting that into best_model.build(input_shape=(None,28,28)) just causes the above error for me.

I used this function to build my model:

def build_model(hp):
    model = keras.Sequential()
    model.add(layers.Flatten())
    for i in range(hp.Int("num_layers", 1, 3)):
        model.add(
            layers.Dense(
                # Tune number of units separately.
                units=hp.Int(f"units_{i}", min_value=32, max_value=512, step=32),
                activation=hp.Choice("activation", ["relu", "tanh"]),
            )
        )
    if hp.Boolean("dropout"):
        model.add(layers.Dropout(rate=0.25))
    model.add(layers.Dense(1, activation="softmax"))
    learning_rate = hp.Float("lr", min_value=1e-4, max_value=1e-2, sampling="log")
    model.compile(
        optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"],
    )
    return model

and used this code to return the model

tuner = kt.RandomSearch(
    build_model,
    objective='val_accuracy',
    overwrite=True,
    max_trials=10,
    executions_per_trial=1)
tuner.search(x_train, y_train, epochs=100, validation_data=(x_test, y_test))
best_model = tuner.get_best_models()[0] 

The shape of my input data is (562844, 16), but inputting that as the input_shape returns the error: ValueError: Input 0 of layer "dense" is incompatible with the layer: expected axis -1of input shape to have value 784, but received input with shape (562844, 16).

Any suggestions for finding the right input shape or otherwise fixing the problem would be appreciated.