YJYS_ZHX的博客

1 main中的相关参数#函数：def get_args_parser():parser.add_argument('--input-size', default=224, type=int, help='images input size')#颜色抖动parser.add_argument('--color-jitter', type=float, default=0.4, metavar='PCT', help='Color jitter fac

1 代码作用此代码主要用于数据增强，数据增强相关论文为《Autougment Learning： Augmentation Polices from Data》。2 代码1）导入"""Copy from https://github.com/DeepVoltaire/AutoAugment/blob/master/autoaugment.py"""from PIL import Image, ImageEnhance, ImageOpsimport numpy as npimport r

LambdaLR类：torch.optim.lr_scheduler作用是，可以自定义学习率学习曲线，官方代码如下：lass LambdaLR(_LRScheduler): """Sets the learning rate of each parameter group to the initial lr times a given function. When last_epoch=-1, sets initial lr as lr. Args: optim

1 modeling.py1）导入包# coding=utf-8from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport torchsnooper as tsimport copyimport loggingimport mathfrom os.path import join as pjoinimport to

桃叶儿尖上尖，柳絮儿飞满了天…1 导入库import torchfrom torch import nn, einsumimport torch.nn.functional as Ffrom einops import rearrange, repeatfrom einops.layers.torch import Rearrange解释：其中einops库可以上网上百度，使用还是比较方便的。自己放上一个链接：...