摘要:
#!/usr/bin/python3 # _*_coding:utf-8 _*_ ''' 自定义重写 dataset,实现类别均衡,体现为 每个batch都可以按照自己设定得比例来采样,且支持多进程和分布式 ''' from check_pkgs import * import torch.dist 阅读全文
posted @ 2021-02-06 18:47
dangxusheng
阅读(3003)
评论(0)
推荐(0)
摘要:
import torch import torch.nn as nn import torch.nn.functional as F class LSR(nn.Module): def __init__(self, n_classes=10, eps=0.1): super(LSR, self)._ 阅读全文
posted @ 2021-02-06 18:42
dangxusheng
阅读(1735)
评论(0)
推荐(0)
摘要:
参考博客:http://aiuai.cn/aifarm1340.htmlhttps://yangkky.github.io/2019/07/08/distributed-pytorch-tutorial.html pytorch里DataParallel 和 DistributedParallel 阅读全文
posted @ 2021-02-06 18:28
dangxusheng
阅读(422)
评论(0)
推荐(0)
摘要:
不懂原理的同学请参考: https://blog.csdn.net/qq_43337858/article/details/102738352?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPa 阅读全文
posted @ 2021-02-06 17:55
dangxusheng
阅读(1400)
评论(0)
推荐(0)
浙公网安备 33010602011771号