Closed josephbirkner closed 7 years ago
Currently, the DSLstmPredictor._stepwise_predictor() is feeding itself the previous softmax probability distribution. This leads to a rapid decline in confidence for the predictions, since the network is only trained with one-hot encoded vectors.
Fixed with 51aa078723e91e6c9e2840927e3eaccdcbb616aa
Currently, the DSLstmPredictor._stepwise_predictor() is feeding itself the previous softmax probability distribution. This leads to a rapid decline in confidence for the predictions, since the network is only trained with one-hot encoded vectors.