alphanlp

where final output has no softmax

3

self.logits = tf.layers.dense(self.dec, len(en2idx))

when i use tensorlayer, there is a question

3

TypeError: () got an unexpected keyword argument 'is_last'

when i run the pinyin_main.py, get UserWarning like below

2

UserWarning: Output "lambda_83" missing from loss dictionary. We assume this was done on purpose, and we will not be expecting any data to be passed to "lambda_83" during training. self.model.compile(optimizer,...

maybe i find a point should be change

2

self.target_layer = TimeDistributed(Dense(o_tokens.num(), use_bias=False)) change to: self.target_layer = TimeDistributed(Dense(o_tokens.num(), activation='softmax', use_bias=False))

benebot_vector 和config

2

benebot_vector 和config 是什么？源码中没有，也没有相应模块

why the input_size of Linear if 2?

torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean')[SOURCE] This criterion combines nn.LogSoftmax() and nn.NLLLoss() in one single class. I guess F.softmax(logits) and CrossEntropyLoss() used together is wrong?