update readme

hycis · hycis · commit 82862cbea715 · 2018-03-18T02:08:44.000+08:00
diff --git a/README.md b/README.md
@@ -73,13 +73,13 @@ class ModelB(BaseModel):
         self.endnode = tg.EndNode(prev=[hn])
 ```
 
-creating a layer only created all the `Variables`. To connect the `Variables` into a graph, you can do a `_train_fprop(X)` or `_test_fprop(X)` to create the tensorflow graph. By abstracting `Variable` creation away from linking the `Variable` nodes into graph prevent the problem of certain tensorflow layers that always reinitialise its weights when it's called, example the [`tf.nn.batch_normalization`](https://www.tensorflow.org/api_docs/python/tf/nn/batch_normalization) layer. Also having a separate channel for training and testing is to cater to layers with different training and testing behaviours such as batchnorm and dropout.
+creating a layer only created all the `Variables`. To connect the `Variables` into a graph, you can do a `train_fprop(X)` or `test_fprop(X)` to create the tensorflow graph. By abstracting `Variable` creation away from linking the `Variable` nodes into graph prevent the problem of certain tensorflow layers that always reinitialise its weights when it's called, example the [`tf.nn.batch_normalization`](https://www.tensorflow.org/api_docs/python/tf/nn/batch_normalization) layer. Also having a separate channel for training and testing is to cater to layers with different training and testing behaviours such as batchnorm and dropout.
 
 ```python
 modelb = ModelB()
 X_ph = tf.placeholder()
-y_train = modelb._train_fprop(X_ph)
-y_test = modelb._test_fprop(X_ph)
+y_train = modelb.train_fprop(X_ph)
+y_test = modelb.test_fprop(X_ph)
 ```
 
 checkout some well known models in TensorGraph
@@ -102,8 +102,8 @@ hvd.init()
 modelb = ModelB()
 X_ph = tf.placeholder()
 y_ph = tf.placeholder()
-y_train = modelb._train_fprop(X_ph)
-y_test = modelb._test_fprop(X_ph)
+y_train = modelb.train_fprop(X_ph)
+y_test = modelb.test_fprop(X_ph)
 
 train_cost = mse(y_train, y_ph)
 test_cost = mse(y_test, y_ph)
