cocowf

In dataset.py ,a notation about variable graph is 'if self.train: # only training data has fst (graph)',which means valid and test do not need have variable graph,but in the train.py,the...

Thanks Yiwen,there is another question. you mean is that valid/test do not have attribution sample['graph'],but in loss function ,criterion(outputs, output_lengths, graphs).when we skip empty graph in valid/test,how does valid loss...

by skipping the utterance with empty graph, it means minibatch is non-empty graph?

"An empty graph encountered!" occured before skipping the empty graph ,because of graph = ChainGraph(fst, log_domain=True),raise Exception in pychain/graph.py.

Thx,when delete https://github.com/YiwenShaoStephen/pychain/blob/master/pychain/graph.py#L69,it's ok

I was doubt ,before skipping why a little valid set has non-empty graph.but all empty graph

> @busishengui Did you ever resolve this issue? Having similar issues on a different dataset. Did you ever use this pychain in different dataset ,such as mandarin,how did files related...

how to edit deploy.prototxt about two input of ip2 layer?where is bottom :label source from?

the same question :the deploy.prototxt of LargeMargin_Softmax_Loss？ How to edit deploy.prototxt

@QQQYang Is it necessary that I compile the attentioncrop layer and rank loss in my own caffe firstly ,secondly I can use train.prototxt?