您好，我在读取数据遇到了IndexError: too many indices for array的问题

[userpei]

Traceback (most recent call last):
File "train.py", line 155, in
train(opt)
File "train.py", line 76, in train
data = loader.get_batch('train')
File "VSUA-Captioning-master/dataloader.py", line 144, in get_batch
ix, tmp_wrapped = self._prefetch_process[split].get()
File "VSUA-Captioning-master/dataloader.py", line 368, in get
tmp = self.split_loader.next()
File "/home/usr2/anaconda2//lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 623, in next
return self._process_next_batch(batch)
File "/home/usr2/anaconda2/envs/pyx/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
File "/home/usr2/anaconda2//lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/VSUA-Captioning-master/dataloader.py", line 253, in getitem
sg_data = self.get_graph_data(index)
File "/VSUA-Captioning-master/dataloader.py", line 277, in get_graph_data
rela['edges'] = triplet[:, 0:2]
IndexError: too many indices for array

[kkunli]

您好，我也在使用semantic relationship时遇到了这个问题，请问解决了吗？

[userpei]

您好，我也在使用semantic relationship时遇到了这个问题，请问解决了吗？

    if sg_use['rela_matrix'].shape[0] == 0:
        sg_use['rela_matrix'] = np.array([[0, 0, self.sg_vocab['near']]], dtype=sg_use['rela_matrix'].dtype)

修改之后，没有报错了

[kkunli]

修改后迭代几次,还是报错,您没发生这个问题吗?

KeyError: 'Traceback (most recent call last):\n File "/home/b604_1/anaconda2/envs/pyli2.7/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "/home/b604_1/aaa/VSUA-Captioning/dataloader.py", line 253, in getitem\n sg_data = self.get_graph_data(index)\n File "/home/b604_1/aaa/VSUA-Captioning/dataloader.py", line 270, in get_graph_data\n sg_use['rela_matrix'] = np.array([[0, 0, self.sg_vocab['near']]], dtype=sg_use['rela_matrix'].dtype)\nKeyError: 'near'\n'