Multiple parameterized metrics in Keras - python-3.x

Question

Let's say I have a custom parameterized metric:
def my_metric_at_k(k):
def my_metric(y_true, y_pred):
'''
Do magic here with k
to get metric_value
'''
return metric_value
return my_metric
I want to evaluate my model with my metric on multiple values of k, say k=1 and k=2, so naturally, I'm inclined to feed [my_metric_at_k(1), my_metric_at_k(2)] into metrics input of the compile method.
When I go to fit my model, I run into this error
NotFoundError: FetchOutputs node metrics/my_metric_1/...: not found
I'm using Keras with a TensorFlow backend.
For a particular example, one metric I use is the following:
def variety_first_k(k):
def variety(y_true, y_pred):
y_pred = K.tf.cast(y_pred, dtype=K.tf.float64)
sort = K.tf.nn.top_k(y_pred, k=k, sorted=True).indices
unique, _ = K.tf.unique(K.flatten(sort))
num_unique = K.shape(unique)[0]
return K.tf.cast(num_unique, dtype=K.tf.float64) /
K.tf.cast(K.tf.shape(y_pred)[1], dtype=K.tf.float64)
return variety
I'm running a multi-label multi-class problem.
A simplified version of my model is:
metrics = [variety_first_k(1), variety_first_k(2)]
inputs = layers.Input(shape=(my_data.shape[1],))
merged_layer = layers.BatchNormalization()(inputs)
merged_layer = layers.Dense(256, activation='relu',
kernel_regularizer=l1_l2(l1=0.5, l2=0.5))(merged_layer)
merged_layer = layers.BatchNormalization()(merged_layer)
predictions = layers.Dense(len(mlb.classes_))(merged_layer)
predictions = layers.Activation('sigmoid')(predictions)
model = keras.Model(inputs=inputs, outputs=predictions)
EPOCHS = 100
INIT_LR = 1e-2
BS = 128
opt = keras.optimizers.Adadelta(lr=INIT_LR, decay=INIT_LR / EPOCHS)
model.compile(loss=multilabel,
optimizer=opt,
metrics=metrics)
H = model.fit(x=my_data,
y=Y,
validation_split=0.02,
epochs=EPOCHS,
batch_size=BS)
The result gives me:
Train on 260563 samples, validate on 5318 samples
Epoch 1/100
...
...
NotFoundError: FetchOutputs node metrics/...: not found