fix #1053

docs/tutorial/symbolic.md

@@ -7,7 +7,7 @@ such as conv/deconv, fc, bn, pooling layers. **You do not need to learn them.**
 These layers were written only because there were no alternatives when
 tensorpack was first developed.
 Nowadays, these implementation actually call `tf.layers` directly.
-Tensorpack will not add any more layers into its core library because this is
+__Tensorpack will not add any more layers__ into its core library because this is
 not the focus of tensorpack, and there are many other alternative symbolic
 libraries today.
 

tensorpack/models/registry.py

@@ -26,6 +26,10 @@ def _register(name, func):
         raise ValueError(logger.error("A layer cannot be named {}".format(name)))
     _LAYER_REGISTRY[name] = func
 
+    # handle alias
+    if name == 'Conv2DTranspose':
+        _register('Deconv2D', func)
+
 
 def get_registered_layer(name):
     """