update dorefa doc

README.md

@@ -15,7 +15,8 @@ See some interesting [examples](examples) to learn about the framework:
 
 Abstract your training task into three components:
 
-1. Model, or graph. `models/` has some scoped abstraction of common models.
+1. Model, or graph. `models/` has some scoped abstraction of common models. This part is roughly an
+	 equivalent of slim/tflearn/tensorlayer.
 	`LinearWrap` and `argscope` makes large models look simpler.
 
 2. Data. tensorpack allows and encourages complex data processing.
@@ -32,7 +33,7 @@ Abstract your training task into three components:
 	+ Send the accuracy to your phone
 
 With the above components defined, tensorpack trainer will run the training iterations for you.
-Multi-GPU training is ready to use by simply switching the trainer.
+Multi-GPU training is off-the-shelf by simply switching the trainer.
 
 ## Dependencies:
 

examples/DoReFa-Net/alexnet-dorefa.py

@@ -289,8 +289,7 @@ if __name__ == '__main__':
     parser.add_argument('--load', help='load a checkpoint, or a npy (given as the pretrained model)')
     parser.add_argument('--data', help='ILSVRC dataset dir')
     parser.add_argument('--dorefa',
-            help='number of bits for W,A,G, separated by comma. Defaults to \'1,2,4\'',
-            default='1,2,4')
+            help='number of bits for W,A,G, separated by comma', required=True)
     parser.add_argument('--run', help='run on a list of images with the pretrained model', nargs='*')
     args = parser.parse_args()