diff options
Diffstat (limited to 'tensorflow/python/ops/distributions/categorical.py')
-rw-r--r-- | tensorflow/python/ops/distributions/categorical.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tensorflow/python/ops/distributions/categorical.py b/tensorflow/python/ops/distributions/categorical.py index dd25fce2ec..fbbacf2521 100644 --- a/tensorflow/python/ops/distributions/categorical.py +++ b/tensorflow/python/ops/distributions/categorical.py @@ -69,7 +69,7 @@ class Categorical(distribution.Distribution): The Categorical distribution is closely related to the `OneHotCategorical` and `Multinomial` distributions. The Categorical distribution can be intuited as generating samples according to `argmax{ OneHotCategorical(probs) }` itself - being identical to `argmax{ Multinomial(probs, total_count=1) }. + being identical to `argmax{ Multinomial(probs, total_count=1) }`. #### Mathematical Details @@ -83,7 +83,7 @@ class Categorical(distribution.Distribution): The number of classes, `K`, must not exceed: - the largest integer representable by `self.dtype`, i.e., - `2**(mantissa_bits+1)` (IEE754), + `2**(mantissa_bits+1)` (IEEE 754), - the maximum `Tensor` index, i.e., `2**31-1`. In other words, |