Kyubyong/transformer
A TensorFlow Implementation of the Transformer: Attention Is All You Need
PythonApache-2.0
Issues
- 1
- 2
请问下,有TF2.X有实现的代码吗
#172 opened by zhanghaobucunzai - 3
- 2
- 2
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[27,100] = 100 is not in [0, 100)
#181 opened by keaiyang222 - 1
about spm.SentencePieceTrainer.Train(train)
#185 opened by Joll123 - 0
About the query_mask
#182 opened by bjuthjliu - 3
enc *= self.d_model**0.5 # scale
#132 opened by qwaiz - 0
- 0
多头问题的实现推导不太理解
#176 opened by frostjsy - 0
train error
#175 opened by JLUForever - 2
something about Model.py , in which something wrong between encoder and decoder
#163 opened by glorymu - 4
自己学习率没有调节好
#164 opened by glorymu - 1
- 4
- 1
- 7
key_mask是什么 what is key_mask in modules's mask????
#140 opened by letmeheard - 1
request for dataset
#171 opened by lhy2749 - 0
- 0
- 2
'gbk' codec can't decode byte 0x93 in position 978: illegal multibyte sequence and then a bytes-like object is required, not 'str'
#146 opened by Ailing-Zou - 0
Error! excuting the train.py
#167 opened by rupjyotiBaruah - 0
Why to remove query masking?
#162 opened by ywl0911 - 0
在moudules中的multi-head attention的实现
#139 opened by letmeheard - 3
training data was used to eval
#157 opened by hihell - 1
how to understand decoder_inputs have ["<s>"] while y_hat, y or x don't have ["<s>"]
#159 opened by bozhenhhu - 0
- 0
- 2
I found a small mistake in the Transformer model.
#158 opened by rhksgud92 - 0
Will there be a TF2.0 version of this project?
#156 opened by Xanyv - 0
- 0
- 0
run test error
#152 opened by anpingbo - 0
Is there a version tf2.0 of this project
#149 opened by ZhichaoOuyang - 3
- 0
Why do you only one vocab? nmt has two languages
#148 opened by nlpofwhat - 1
Best performance on iwslt2016 de->en?
#138 opened by LibertFan - 1
train.py, small logic problems
#143 opened by 915288938lx - 0
ImportError: DLL load failed: The specified module could not be found. Please help me!
#145 opened by zhiyong5 - 1
for _ in tqdm(range(self.hp.maxlen2))
#142 opened by tyongguang - 1
How to get the output without decoder -input?
#134 opened by Yuui-Asuka - 0
positional_encoding , sin cos has the same input ??
#137 opened by bsll - 0
Debugging, errore
#136 opened by kevinwei1975 - 0
Encoding issue
#131 opened by skumyol - 0
- 0
why use tf.sign to deal with mask?
#128 opened by qiaoguan - 2
- 0
prepro.py error, no cutting files
#127 opened by muzixi0429 - 0
how to preprocess the self.x in graph
#126 opened by ai-galgame - 0
X_label of your mean loss?
#125 opened by ArnoldLIULJ