diff options
Diffstat (limited to 'tensorflow/g3doc/tutorials/estimators/index.md')
| -rw-r--r-- | tensorflow/g3doc/tutorials/estimators/index.md | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/tensorflow/g3doc/tutorials/estimators/index.md b/tensorflow/g3doc/tutorials/estimators/index.md index 2fd1a8795c..46a0cf87a1 100644 --- a/tensorflow/g3doc/tutorials/estimators/index.md +++ b/tensorflow/g3doc/tutorials/estimators/index.md @@ -152,6 +152,8 @@ def maybe_download(): print("Training data is downloaded to %s" % train_file_name) if FLAGS.test_data: + test_file_name = FLAGS.test_data + else: test_file = tempfile.NamedTemporaryFile(delete=False) urllib.urlretrieve("http://download.tensorflow.org/data/abalone_test.csv", test_file.name) test_file_name = test_file.name @@ -379,7 +381,7 @@ tf.contrib.layers provides the following convenience functions for constructing fully connected layers: * `relu(inputs, num_outputs)`. Create a layer of `num_outputs` nodes fully - connected to the previous layer `inputs` with a [ReLu activation + connected to the previous layer `inputs` with a [ReLU activation function](https://en.wikipedia.org/wiki/Rectifier_\(neural_networks\)) ([tf.nn.relu](../../api_docs/python/nn.md#relu)): @@ -388,7 +390,7 @@ fully connected layers: ``` * `relu6(inputs, num_outputs)`. Create a layer of `num_outputs` nodes fully - connected to the previous layer `hidden_layer` with a ReLu 6 activation + connected to the previous layer `hidden_layer` with a ReLU 6 activation function ([tf.nn.relu6](../../api_docs/python/nn.md#relu6)): ```python @@ -448,7 +450,7 @@ def model_fn(features, targets, mode, params): Here, because you'll be passing the abalone `Datasets` directly to `fit()`, `evaluate()`, and `predict()` via `x` and `y` arguments, the input layer is the `features` `Tensor` passed to the `model_fn`. The network contains two hidden -layers, each with 10 nodes and a ReLu activation function. The output layer +layers, each with 10 nodes and a ReLU activation function. The output layer contains no activation function, and is [reshaped](../../api_docs/python/array_ops.md#reshape) to a one-dimensional tensor to capture the model's predictions, which are stored in |