dut-liuyang / aspect-sentiment-analysis Goto Github PK

Hi, I got the following message when running Main.py, it seems to be the weight shape problem , any idea on solving it? thanks :
Traceback (most recent call last):
File "Main.py", line 36, in
num_words=4582) # 5144 4582 // # 1523 // 1172
File "/home/syl/Aspec-level/2018-CONLL-HAPN/Aspect-Sentiment-Analysis-master/lib/Model.py", line 63, in build_model
sentence_embedding = sentence_embedding_layer(sentence_input) # (?, 78, 300)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 583, in call
self.set_weights(self._initial_weights)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 1201, in set_weights
'provided weight shape ' + str(w.shape))
ValueError: Layer weight shape (4583, 300) not compatible with provided weight shape (5804, 300)

Hi,

thank u for sharing ur code with us

I tried to reproduce the results but I got this error when executing the data2input file

thank u

请问您实验所用的数据是SemEval 2014的吗？

出现以下问题：
could not convert string to float: 'furuse'

你好，请问一下这个报错应该怎么改？
ValueError: A Concatenate layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 78, 300), (None, 82, 600)]