nvidia-smi에는 잡히지 않는 process가 gpu 메모리를 차지하고 있을 때

 sudo fuser -v /dev/nvidia0

 sudo fuser -v /dev/nvidia1

...

식으로 pid 확인 후 kill


출처: https://stackoverflow.com/questions/59431784/gpu-ram-occupied-but-no-pids

댓글

댓글 쓰기

이 블로그의 인기 게시물

sklearn tsne + matplotlib scatter

import os import torch import clip import matplotlib . pyplot as plt from PIL import Image from sklearn . manifold import TSNE from tqdm import tqdm from collections import defaultdict from random import shuffle   X = torch . cat ( X , dim = 0 ) X_emb = TSNE ( init = "pca" , perplexity = 30.0 ). fit_transform ( X . cpu ()) labels = [ "source" , "z_star/foggy-1" , "z_star/foggy-2" , "z_star/foggy-3" , "z_bar/foggy-1" , "z_bar/foggy-2" , "z_bar/foggy-3" ] fig , ax = plt . subplots ( 1 ) group_len = len ( zs ) for i in range ( 7 ): ax . scatter ( X_emb [ i * group_len :( i + 1 )* group_len , 0 ], X_emb [ i * group_len :( i + 1 )* group_len , 1 ], label = labels [ i ], s = 4 ) ax . legend () fig .savefig( "temp.png" )
자세한 내용 보기

Implementation of Focal Loss using Pytorch

import torch import torch.nn as nn class BinaryFocalLossWithLogits(nn.Module): def __init__ ( self , gamma= 0 , alpha_dominant= None, reduce= True ): super (BinaryFocalLossWithLogits , self ). __init__ () self .gamma = gamma self .alpha = alpha_dominant self .reduce = reduce self .BCELoss = nn.BCEWithLogitsLoss( reduction = 'mean' if self .reduce else 'none' ) def forward ( self , inputs , labels): loss = self .BCELoss(inputs , labels) pt = torch.exp(- 1 * loss) at = torch.tensor( list ( map ( lambda x: self .alpha if x == 1 else 1 - self .alpha , labels.view(- 1 ).tolist()))) loss = loss * (( 1 - pt) ** self .gamma) * at if self .reduce: return torch.mean(loss) else : return loss usage: criterion = BinaryFocalLossWithLogits( gamma = 2 , alpha_dominant = 0.1 , reduce = False ) labels = torch.tensor([[ 1. , 0. , 0. ]]) output = torch.tensor([[- 0...
자세한 내용 보기