Qiita Teams that are logged in
You are not logged in to any team

Log in to Qiita Team
Community
OrganizationAdvent CalendarQiitadon (β)
Service
Qiita JobsQiita ZineQiita Blog
10
Help us understand the problem. What is going on with this article?
@meipuru344

PyTorchで巨大テンソルのLossを計算していたらメモリ不足になった

More than 1 year has passed since last update.

事の経緯

動画を処理する機械学習コードで

巨大なループの中で誤差を蓄積したかった

for n in range(len(datalist)):

     (省略)
     loss = loss_fn(GroundTruth, output)
     loss.backward()
     losssum += loss
print(losssum/len(datelist))

するどどんどんメモリが圧迫されていき

out of memoryエラーに。。。。

原因

lossテンソルをそのままコピーしていたために

losssum内に勾配データが蓄積されてしまったのが原因みたいだった

正しくは

for n in range(len(datalist)):

     (省略)
     loss = loss_fn(GroundTruth, output)
     loss.backward()
     losssum += loss.detach()
print(losssum/len(datelist))

メモリ問題も解消

教訓

学習に関係ないところにテンソルをコピーするときは

tensor.detach()
#どうやらdetach()はコピー元と同じ記憶領域を共有しているみたいなので
tensor.clone()
#を推奨します!
10
Help us understand the problem. What is going on with this article?
Why not register and get more from Qiita?
  1. We will deliver articles that match you
    By following users and tags, you can catch up information on technical fields that you are interested in as a whole
  2. you can read useful information later efficiently
    By "stocking" the articles you like, you can search right away
meipuru344
機械学習を勉強している学生です

Comments

No comments
Sign up for free and join this conversation.
Sign Up
If you already have a Qiita account Login
10
Help us understand the problem. What is going on with this article?