Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for scanJar (0.07 sec)

  1. RELEASE.md

            Keras training loops like `fit`/`evaluate`, the unreduced vector loss is
            passed to the optimizer but the reported loss will be a scalar value.
        *   `SUM`: Scalar sum of weighted losses. 4. `SUM_OVER_BATCH_SIZE`: Scalar
            `SUM` divided by number of elements in losses. This reduction type is
            not supported when used with `tf.distribute.Strategy` outside of
    Registered: Tue Nov 05 12:39:12 UTC 2024
    - Last Modified: Tue Oct 22 14:33:53 UTC 2024
    - 735.3K bytes
    - Viewed (0)
Back to top