rename & update readme

README.md

@@ -4,7 +4,7 @@ Neural Network Toolbox on TensorFlow
 [![Build Status](https://travis-ci.org/ppwwyyxx/tensorpack.svg?branch=master)](https://travis-ci.org/ppwwyyxx/tensorpack)
 [![badge](https://readthedocs.org/projects/pip/badge/?version=latest)](http://tensorpack.readthedocs.io/en/latest/index.html)
 
-Tutorials are not fully finished. See some [examples](examples) to learn about the framework:
+Tutorials are not finished. See some [examples](examples) to learn about the framework:
 
 ### Vision:
 + [DoReFa-Net: train binary / low-bitwidth CNN on ImageNet](examples/DoReFa-Net)

examples/ResNet/README.md

@@ -16,7 +16,7 @@ To train, just run:
 ```bash
 ./imagenet-resnet.py --data /path/to/original/ILSVRC --gpu 0,1,2,3 -d 18
 ```
-The speed is 1860 samples/s on 4 TitanX Pascal, and 1160 it/s on 4 old TitanX, provided that your data is fast
+The speed is 1860 samples/s on 4 TitanX Pascal, and 1160 samples/s on 4 old TitanX, if your data is fast
 enough. See the [tutorial](http://tensorpack.readthedocs.io/en/latest/tutorial/efficient-dataflow.html) on how to speed up your data.
 
 ![imagenet](imagenet-resnet.png)

examples/SimilarityLearning/mnist-embeddings.py

@@ -98,7 +98,7 @@ class CosineModel(SiameseModel):
         with tf.variable_scope(tf.get_variable_scope(), reuse=True):
             tf.identity(self.embed(inputs[0]), name="emb")
 
-        cost = symbf.cosine_loss(x, y, label, scope="loss")
+        cost = symbf.siamese_cosine_loss(x, y, label, scope="loss")
         self.cost = tf.identity(cost, name="cost")
         add_moving_summary(self.cost)
 

tensorpack/tfutils/symbolic_functions.py

@@ -257,7 +257,7 @@ def contrastive_loss(left, right, y, margin, extra=False, scope="constrastive_lo
             return loss
 
 
-def cosine_loss(left, right, y, scope="cosine_loss"):
+def siamese_cosine_loss(left, right, y, scope="cosine_loss"):
     r"""Loss for Siamese networks (cosine version).
     Same as :func:`contrastive_loss` but with different similarity measurement.