diff options
| -rw-r--r-- | tensorflow/docs_src/mobile/mobile_intro.md | 2 | ||||
| -rw-r--r-- | tensorflow/python/ops/distributions/multinomial.py | 2 |
2 files changed, 2 insertions, 2 deletions
diff --git a/tensorflow/docs_src/mobile/mobile_intro.md b/tensorflow/docs_src/mobile/mobile_intro.md index 17dbf1c3e6..69b63ae7d2 100644 --- a/tensorflow/docs_src/mobile/mobile_intro.md +++ b/tensorflow/docs_src/mobile/mobile_intro.md @@ -235,7 +235,7 @@ TensorFlow [on Github](https://github.com/tensorflow/models) that you can look through. Lean towards the simplest model you can find, and try to get started as soon as you have even a small amount of labelled data, since you’ll get the best results when you’re able to iterate quickly. The shorter the time it takes to -try training a model and running it in s real application, the better overall +try training a model and running it in its real application, the better overall results you’ll see. It’s common for an algorithm to get great training accuracy numbers but then fail to be useful within a real application because there’s a mismatch between the dataset and real usage. Prototype end-to-end usage as soon diff --git a/tensorflow/python/ops/distributions/multinomial.py b/tensorflow/python/ops/distributions/multinomial.py index 26b5c5aef9..4ae67a009b 100644 --- a/tensorflow/python/ops/distributions/multinomial.py +++ b/tensorflow/python/ops/distributions/multinomial.py @@ -238,7 +238,7 @@ class Multinomial(distribution.Distribution): n_draws = math_ops.cast(self.total_count, dtype=dtypes.int32) k = self.event_shape_tensor()[0] - # boardcast the total_count and logits to same shape + # broadcast the total_count and logits to same shape n_draws = array_ops.ones_like( self.logits[..., 0], dtype=n_draws.dtype) * n_draws logits = array_ops.ones_like( |