使用 gpu运行出现TypeError: 'generator' object is not subscriptable？

Question

使用 gpu运行出现TypeError: 'generator' object is not subscriptable？

cjjjy opened this issue 4 years ago · comments

你好，我使用gpu运行您的代码时出现以下错误，我的pytorch 版本是0.4.1：
self.check_forward_args(input, hx, batch_sizes)
File "/home/nlp/anaconda2/envs/Bert-BiLSTM-CRF-pytorch/lib/python3.5/site-packages/torch/nn/modules/rnn.py", line 146, in check_forward_args
check_hidden_size(hidden[0], expected_hidden_size,
TypeError: 'generator' object is not subscriptable

ken19980727 commented 4 years ago

謝謝您

zxy_kkk · Answer 1 · Thu Oct 01 2020 09:39:02 GMT+0800 (China Standard Time)

你好，我使用gpu运行您的代码时出现以下错误，我的pytorch 版本是0.4.1：
self.check_forward_args(input, hx, batch_sizes)
File "/home/nlp/anaconda2/envs/Bert-BiLSTM-CRF-pytorch/lib/python3.5/site-packages/torch/nn/modules/rnn.py", line 146, in check_forward_args
check_hidden_size(hidden[0], expected_hidden_size,
TypeError: 'generator' object is not subscriptable

解决了，将
hidden = (i.cuda() for i in hidden)这行代码改成下面即可运行：
hidden1=hidden[0].cuda()
hidden2=hidden[1].cuda()
hidden=(hidden1,hidden2)