Python: model.fit() error, None values not supported

Question

I am working with CNN project to classify a sequence of pitch. The pitch class has a total of 51 classes, meaning I want to classify 51 pitches available in a dataset.

For the metrics, I plan to use Precision, Recall, F1 score. I refer to this post to make the function like this:

Functions I made:

from keras import backend as K

def recall_m(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
    recall = true_positives / (possible_positives + K.epsilon())
    return recall

def precision_m(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())
    return precision

def f1_m(y_true, y_pred):
    precision = precision_m(y_true, y_pred)
    recall = recall_m(y_true, y_pred)
    return 2*((precision*recall)/(precision+recall+K.epsilon()))

Model operation I made with metrics=['accuracy', f1_m, precision_m, recall_m]

epochs = 200
batch_size = 50
weight_optimizer = keras.optimizers.Adam(lr=0.0001)

with tf.device('/device:GPU:0'):
  model.compile(optimizer = weight_optimizer , loss = "categorical_crossentropy", metrics=['accuracy', f1_m, precision_m, recall_m]])
  history = model.fit(X_train, y_train, batch_size = batch_size, epochs = epochs, verbose = 1, validation_split=0.1)

And I got this error:

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step  **
        outputs = model.train_step(data)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:758 train_step
        self.compiled_metrics.update_state(y, y_pred, sample_weight)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:408 update_state
        metric_obj.update_state(y_t, y_p, sample_weight=mask)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/metrics_utils.py:90 decorated
        update_op = update_state_fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/metrics.py:177 update_state_fn
        return ag_update_state(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/metrics.py:620 update_state  **
        matches, sample_weight=sample_weight)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/metrics.py:355 update_state
        values = math_ops.cast(values, self._dtype)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py:964 cast
        x = ops.convert_to_tensor(x, name="x")
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/profiler/trace.py:163 wrapped
        return func(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:1540 convert_to_tensor
        ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py:339 _constant_tensor_conversion_function
        return constant(v, dtype=dtype, name=name)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py:265 constant
        allow_broadcast=True)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py:283 _constant_impl
        allow_broadcast=allow_broadcast))
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_util.py:445 make_tensor_proto
        raise ValueError("None values not supported.")

    ValueError: None values not supported.

If I delete the f1_m, precision_m, recall_m from metrics, I don't get any error. Is there any clues on how to include those f1_m, precision_m, recall_m in metrics without getting that None values error? Or is it because my classification is not binary? Thank you.

Answer 1

As per this thread you should change the optimizer to this:

optimizer = "adam"

Also your fucntion f1_m is incomplete and should be this.

def f1_m(y_true, y_pred):
    precision = precision_m(y_true, y_pred)
    recall = recall_m(y_true, y_pred)
    return 2*((precision*recall)/(precision+recall+K.epsilon()))