OOM about pytorch_speaker_verification HOT 17 CLOSED

@gurul hello　，Ｉ　am run the project ues my own datasets! have you meet the issue below

from pytorch_speaker_verification.

@gurul hello　，Ｉ　am run the project ues my own datasets! have you meet the issue below

**人我就说中文了哈，方便表达一点。
没遇到过，提示的是 utterance 的indice越界了，你看看 utterance 的维度对不对，对比一下作者用的默认TIMIT 数据输出的 utterance 的维度是多少

from pytorch_speaker_verification.

@gurul 我没有下载ＴＩＭＩＴ数据集，那个太大了．你用的ＴＩＭＩＴ数据集是这样的呢，可以截个图吗，我是用的aishell生成的npy,是这样的：

test_tisv文件夹有几十个npy,train_tisv文件夹有３６０个npy的样子

from pytorch_speaker_verification.

The config defaults to using your GPU. If you want to use your cpu, change the following line in the config.yaml:

device: "cuda"

If you still run out of memory, try reducing the batch size.

from pytorch_speaker_verification.

@HarryVolek
Thank you for your reply!
I have changed this config to
device: 'CPU'
And I try to used only one sample in one batch, it also get a OOM error. Could you tell me what operating system do you use? My friend try to run this code on Win 7 do not meet this problem.
And Could you tell me Which GPU you are used to train?

from pytorch_speaker_verification.

@Aurora11111
不是这个意思老哥
我指的是utterance这个数组你看下你的shape的维度是不是有三维，看报的错误估计和你的utterance维度有关系。npz个数和这个没关系。是npz里面的数据的维度的问题。
然后我咨询一下，TIMIT这个库很大吗，我为啥只下了400多M，如果你找到的比这个多，能分享下你找到的连接吗，我现在需要再找点数据

from pytorch_speaker_verification.

@gurul 我下载下来是个种子文件．torrent格式的，确实是４００Ｍ，你是用的这个吗，怎么打开的，打开还是只有４００Ｍ吗．
我的npz里的数据维度确实维度比较少
http://academictorrents.com/details/34e2b78745138186976cbc27939b1b34d18bd5b3

from pytorch_speaker_verification.

@Aurora11111
TIMIT的话，按下面这个目录放到项目的根目录，前面几层的文件夹删掉
'./TIMIT////.wav'
在README里有介绍
你可以看下作者处理音频的代码，处理TIMIT的和处理你那个数据集的有啥不同

from pytorch_speaker_verification.

@gurul 恩，我用百度网盘打开了，但是我这个系统无法下载，我　的数据集是aishell,我还是想想办法怎么用这个ＴＩＭＩＴ吧

from pytorch_speaker_verification.

@gurul I run Ubuntu. The model shouldn't be difficult to train, people have trained comparable models with CPUs. Either way, I believe the issue is with your hardware and not the code itself, so I am closing.

from pytorch_speaker_verification.

When I wrote the code I was using a GTX 970 to train.

from pytorch_speaker_verification.

yeah ! after I change to TIMIT datasets it run succesfully. thank you! @gurul

from pytorch_speaker_verification.

When I wrote the code I was using a GTX 970 to train.

Thank you very much! And thank you for opening the source code! It helps me a lot.

from pytorch_speaker_verification.

yeah ! after I change to TIMIT datasets it run succesfully. thank you! @gurul

Welcome

from pytorch_speaker_verification.

I have trained on default config (exept with 'device: "cpu"') and encountered OOM error.

My dependencies:

• PyTorch 1.0.1.post2
• python 3.7 with anaconda
• numpy 1.15.4
• librosa 0.6.3

I don't know why it was happen.
Sorry for my bad English.

from pytorch_speaker_verification.

07f996a

Try again with the latest commit @trunglebka .

from pytorch_speaker_verification.

Sorry for reply lately
I have updated your code to the lastest commit but OOV still there :(

from pytorch_speaker_verification.