zxy_kkk

Always connecting...

5

Hi ,I install this project follow your steps on the linux server, (1)docker-compose up -d (2)docker-compose logs -f and it has no error and running sucessfully,LOG AS FOLLOWS: ....... kaldi_1...

ResourceExhaustedError: OOM when allocating tensor with shape

2

HI when I run timit_train.py, error as follow , how can I slove it? 2018-06-08 17:26:00.908082: I tensorflow/core/common_runtime/bfc_allocator.cc:680] Stats: Limit: 10625279591 InUse: 7350513920 MaxInUse: 7464792320 NumAllocs: 82 MaxAllocSize: 3656908800 2018-06-08...

Hi: WHEN I TRY TO RUN THE COOMMAND : python3 timit_train.py --mode train --level cha --batch_size 8 IT PRODUCE THE PROBLEM AS FOLLOWS: 2018-01-14 14:23:26.356409: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device...

Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)

1

I run the code 3 - Neural Machine Translation by Jointly Learning to Align and Translate.ipynb。it come across error: /home/caoyang/anaconda2/envs/pytorch-seq2seq/bin/python /home/caoyang/home/caoyang/pycharm-2017.3.3/helpers/pydev/pydevd.py --multiproc --qt-support=auto --client 127.0.0.1 --port 36485 --file /home/caoyang/nlp_cuobiezi/pytorch-seq2seq-master/3.py pydev...

训练时GPU利用率低

1

 你好，我想问下我训练BILSTM时，发现GPU 的利用率比较低只有11%左右，需要设置什么吗？

Awful: Nnet rejected

1

I try running the command , ./rnnlm -rnnlm model_name -train train.txt -valid valid.txt -hidden 256 -hidden-type gru -nce 20 -alpha 0.01 and it occur the error: entropy (bits) valid: -nan...

problem during runing run_kt.sh

2

Hi, when i run the sh run_kt.sh ,it occur the problem as follows: The path is train=/kaldi-trunk/egs/timit/s5/data/train test=/kaldi-trunk/egs/timit/s5/data/test lang=/kaldi-trunk/egs/timit/s5/data/lang gmm=/kaldi-trunk/egs/timit/s5/exp/tri2 exp=/kaldi-trunk/egs/timit/s5/exp/dnn4_pretrain-dbn_dnn_smbr Is my path set wrong that lead to the...

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

2

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

cnki批量下载结果都是full caj text 链接

4

你好，我想问下我使用jasminum批量下载cnki的论文时，下载结果都是full caj text 的链接snapshot，但是点击论文主页能够下载pdf文件

 装了zotero7 refernce 插件后，参考文献是知网中的文献显示no abstract found，注册了知网研学的账号，