update readme

README.md

-Convolutional Recurrent Neural Network
+Robust Scene Text Recognition with Automatic Rectification
 ======================================
 
-This software implements the Convolutional Recurrent Neural Network (CRNN) in pytorch.
-Origin software could be found in [crnn](https://github.com/bgshih/crnn)
-
-Run demo
---------
-A demo program can be found in ``src/demo.py``. Before running the demo, download a pretrained model
-from [Baidu Netdisk](https://pan.baidu.com/s/1pLbeCND) or [Dropbox](https://www.dropbox.com/s/dboqjk20qjkpta3/crnn.pth?dl=0). 
-This pretrained model is converted from auther offered one by ``tool``.
-Put the downloaded model file ``crnn.pth`` into directory ``data/``. Then launch the demo by:
-
-    python demo.py
-
-The demo reads an example image and recognizes its text content.
-
-Example image:
-![Example Image](./data/demo.png)
-
-Expected output:
-    loading pretrained model from ./data/crnn.pth
-    a-----v--a-i-l-a-bb-l-ee-- => available
-
-Dependence
-----------
-* [warp_ctc_pytorch](https://github.com/SeanNaren/warp-ctc/tree/pytorch_bindings/pytorch_binding)
-* lmdb
-
-Train a new model
------------------
-1. Construct dataset following origin guide. For training with variable length, please sort the image according to the text length.
-2. ``python crnn_main.py [--param val]``. Explore ``crnn_main.py`` for details.
-
-
-Stable commits
---------------
-dbe73da0dd7efb8bd76dbd7f0ac3856e742b98d4: support image list with label and alphabet
+This software implements the Robust Scene Text Recognition with Automatic Rectification (SRN only) in pytorch.
 
 Train for VGG text data
 --------------

models/crnn.py

@@ -118,7 +118,7 @@ class CRNN(nn.Module):
         self.rnn = nn.Sequential(
             BidirectionalLSTM(512, nh, nh),
             BidirectionalLSTM(nh, nh, nh))
-        self.attention = Attention(nh, nh/2, nclass)
+        self.attention = Attention(nh, nh, nclass)
 
     def forward(self, input, length):
         # conv features