# Custom Loss Function: "ValueError: No gradients provided for any variable"

**URL:** <https://discuss.ai.google.dev/t/custom-loss-function-valueerror-no-gradients-provided-for-any-variable/32109>\
**Category:** General Discussion\
**Tags:** recommenders, keras, custom-loss\
**Created:** [June 13, 2023, 9:28pm UTC](https://discuss.ai.google.dev/t/custom-loss-function-valueerror-no-gradients-provided-for-any-variable/32109 "2023-06-13T21:28:05Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rcauvin](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/rcauvin/32/10360_2.png) [@rcauvin](https://discuss.ai.google.dev/u/rcauvin)\
**Post date:** [June 13, 2023, 9:28pm UTC](https://discuss.ai.google.dev/t/custom-loss-function-valueerror-no-gradients-provided-for-any-variable/32109/1 "2023-06-13T21:28:05Z")

</div>

I’m trying to implement a custom loss function, in this case one to minimize top 10 categorical accuracy of a TensorFlow Recommenders two-tower retrieval model.

Unfortunately, no matter what I try, I receive a “ValueError: No gradients provided for any variable” error when fitting my model.

See the loss function code below.

```auto
import tensorflow as tf

class Top10CategoricalAccuracy(tf.keras.losses.Loss):

  def __init__ (
    self, 
    name='top10_categorical_accuracy'):

    super(). __init__ (name=name)

  def call(
    self,
    y_true,
    y_pred,
    sample_weight = None):

    # Convert the predictions to a categorical distribution.
    y_pred = tf.keras.backend.softmax(y_pred)

    # Compute the top 10 accuracy.
    top_10_accuracy = tf.keras.metrics.top_k_categorical_accuracy(y_true, y_pred, k=10)

    # Return the loss.
    return 1.0 - top_10_accuracy

```

The error disappears if I instead delegate to the built-in tf.keras.losses.CategoricalCrossentropy loss function:

```auto
    self.cce_loss_calculator = tf.keras.losses.CategoricalCrossentropy(from_logits = True);
    return self.cce_loss_calculator(y_true, y_pred, sample_weight)

```

How can I implement a custom loss function that doesn’t complain about “no gradients”?