diff options
Diffstat (limited to 'tensorflow/contrib/eager/python/examples/notebooks/2_gradients.ipynb')
| -rw-r--r-- | tensorflow/contrib/eager/python/examples/notebooks/2_gradients.ipynb | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/tensorflow/contrib/eager/python/examples/notebooks/2_gradients.ipynb b/tensorflow/contrib/eager/python/examples/notebooks/2_gradients.ipynb index 3b7e2cd435..e6c7c11733 100644 --- a/tensorflow/contrib/eager/python/examples/notebooks/2_gradients.ipynb +++ b/tensorflow/contrib/eager/python/examples/notebooks/2_gradients.ipynb @@ -383,7 +383,7 @@ "\n", "`implicit_value_and_gradients()` returns a function that accepts the same inputs as the function passed in, and returns a tuple consisting of:\n", "\n", - "1. the value returned by the function passed in (in this case, the loss calculated by `calculate_linear_model_loss()`), and\n", + "1. the value returned by the function passed in (in this case, the loss calculated by `loss_fn()`), and\n", "1. a list of tuples consisting of:\n", " 1. The value of the gradient (a `tf.Tensor`) with respect to a given variable\n", " 1. The corresponding variable (`tf.Variable`)\n", @@ -698,7 +698,7 @@ "source": [ "## Other Ways to Compute Gradients\n", "\n", - "Using our loss function as an example (`calculate_linear_model_loss()`), there are several other ways we could compute gradients:\n", + "Using our loss function as an example (`loss_fn()`), there are several other ways we could compute gradients:\n", "\n", "1. `tfe.implicit_gradients()`\n", "1. `tfe.gradients_function()`\n", @@ -841,7 +841,7 @@ "# tfe.implicit_value_and_gradients() demo\n", "value_gradients_fn = tfe.implicit_value_and_gradients(loss_fn)\n", "\n", - "# Returns only gradients:\n", + "# Returns the value returned by the function passed in, gradients, and variables:\n", "value_gradients_fn(inputs, labels, wb)" ] } |