CODEWITHSUNDEEP
tensorflowkerasloss-function
user3337758
user3337758

Reputation: 115

What is the Tensorflow loss equivalent of "Binary Cross Entropy"?

I'm trying to rewrite a Keras graph into a Tensorflow graph, but wonder which loss function is the equivalent of "Binary Cross Entropy". Is it tf.nn.softmax_cross_entropy_with_logits_v2?

Thanks a lot!

Upvotes: 1

Views: 6156

Answers (1)

DocDriven
DocDriven

Reputation: 3974

No, the implementation of the binary_crossentropy with tensorflow backend is defined here as

@tf_export('keras.backend.binary_crossentropy')
def binary_crossentropy(target, output, from_logits=False):
    """Binary crossentropy between an output tensor and a target tensor.
    Arguments:
      target: A tensor with the same shape as `output`.
      output: A tensor.
      from_logits: Whether `output` is expected to be a logits tensor.
          By default, we consider that `output`
          encodes a probability distribution.
    Returns:
      A tensor.
    """
    # Note: nn.sigmoid_cross_entropy_with_logits
    # expects logits, Keras expects probabilities.
    if not from_logits:
        # transform back to logits
        epsilon_ = _to_tensor(epsilon(), output.dtype.base_dtype)
        output = clip_ops.clip_by_value(output, epsilon_, 1 - epsilon_)
        output = math_ops.log(output / (1 - output))
    return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)

Therefore, it uses sigmoid_crossentropy and not softmax_crossentropy.

Upvotes: 4

Related Questions