Giter VIP home page Giter VIP logo

Comments (7)

HarukiYqM avatar HarukiYqM commented on July 23, 2024

你好,你的gpu里有其他程序把显存占满了。NLSN可以在8G的显卡上训练。

from non-local-sparse-attention.

XiaoZhang-NN avatar XiaoZhang-NN commented on July 23, 2024

你好,你的gpu里有其他程序把显存占满了。NLSN可以在8G的显卡上训练。

谢谢您的回复。我用的是v100,训练用的是800张DIV2K测试用的是10张DIV2K,训练完后,紧接着用10张DIV2K测试时(用于选择最佳模型)显示内存不够了,请问这个原因是?您对数据进行了额外处理?

from non-local-sparse-attention.

HarukiYqM avatar HarukiYqM commented on July 23, 2024

需要训练命令中加入—chop。这是一个sr中比较常用的方法(例如RCAN/SAN/CSNLN)将大图切成四块,用来缓解测试时的显存占用。可以参考readme里的训练命令
python main.py --dir_data ../../ --n_GPUs 4 --rgb_range 1 --chunk_size 144 --n_hashes 4 --save_models --lr 1e-4 --decay 200-400-600-800 --epochs 1000 --chop --save_results --n_resblocks 32 --n_feats 256 --res_scale 0.1 --batch_size 16 --model NLSN --scale 2 --patch_size 96 --save NLSN_x2 --data_train DIV2K

from non-local-sparse-attention.

XiaoZhang-NN avatar XiaoZhang-NN commented on July 23, 2024

需要训练命令中加入—chop。这是一个sr中比较常用的方法(例如RCAN/SAN/CSNLN)将大图切成四块,用来缓解测试时的显存占用。可以参考readme里的训练命令
python main.py --dir_data ../../ --n_GPUs 4 --rgb_range 1 --chunk_size 144 --n_hashes 4 --save_models --lr 1e-4 --decay 200-400-600-800 --epochs 1000 --chop --save_results --n_resblocks 32 --n_feats 256 --res_scale 0.1 --batch_size 16 --model NLSN --scale 2 --patch_size 96 --save NLSN_x2 --data_train DIV2K

特别感谢,麻烦您了,我试试看。

from non-local-sparse-attention.

cheun726 avatar cheun726 commented on July 23, 2024

你好,你的gpu里有其他程序把显存占满了。NLSN可以在8G的显卡上训练。

x3,x4的都可以在8G的卡上训练吗?为什么我x2的就不可以在11G的卡上训练?两张11G的可以,我看了一下内存占用大概是16G,并且没有其他程序占用显存。

from non-local-sparse-attention.

XiaoZhang-NN avatar XiaoZhang-NN commented on July 23, 2024

你好,你的gpu里有其他程序把显存占满了。NLSN可以在8G的显卡上训练。

x3,x4的都可以在8G的卡上训练吗?为什么我x2的就不可以在11G的卡上训练?两张11G的可以,我看了一下内存占用大概是16G,并且没有其他程序占用显存。

您好,我是用的小模型--n_resblocks 8--n_feats 64 所以加上-chop之后就可以运行了。不知道是否符合您的问题。

from non-local-sparse-attention.

cheun726 avatar cheun726 commented on July 23, 2024

谢谢您,我用的32个residual blocks,减小了应该可以。

from non-local-sparse-attention.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.