摘要: # -*- coding: utf-8 -*- """ Created on Tue Dec 27 09:32:02 2016 @author: http://blog.csdn.net/lql0716 """ import cv2 import numpy as np current_pos = 阅读全文
posted @ 2020-04-17 11:57 LifeExp 阅读(1691) 评论(0) 推荐(0)
摘要: https://baijiahao.baidu.com/s?id=1664048285442032934&wfr=spider&for=pc 阅读全文
posted @ 2020-04-17 11:56 LifeExp 阅读(136) 评论(0) 推荐(0)
摘要: https://www.pytorchtutorial.com/pytorch-transfer-learning/ 阅读全文
posted @ 2020-03-14 16:36 LifeExp 阅读(694) 评论(0) 推荐(0)
摘要: https://blog.csdn.net/weixin_44058333/article/details/92691656 1、Motivation: I wanna modify the value of some param; I wanna check the value of some p 阅读全文
posted @ 2020-03-11 13:12 LifeExp 阅读(7938) 评论(0) 推荐(0)
摘要: https://blog.csdn.net/u014380165/article/details/79119664 1. 构建预训练模型:pretrained=True import torchvision.models as models resnet18 = models.resnet18(pr 阅读全文
posted @ 2020-03-02 19:06 LifeExp 阅读(2369) 评论(0) 推荐(0)
摘要: import torch x = torch.randn(2,1,7,3) conv = torch.nn.Conv2d(1,8,(2,3)) res = conv(x) print(res.shape) # shape = (2, 8, 6, 1) 输入x: [ batch_size, chann 阅读全文
posted @ 2020-03-02 18:43 LifeExp 阅读(47339) 评论(2) 推荐(4)
摘要: https://zhuanlan.zhihu.com/p/31852747 ResNet: 深度残差网络。 解决了深度CNN模型训练难的问题。 - 14年VGG 19层;15年ResNet 152层; - 靠深度取胜;利用残差学习使网络的深度发挥出作用。 1. 深度网络的退化问题 [Degradat 阅读全文
posted @ 2020-03-02 15:15 LifeExp 阅读(49) 评论(0) 推荐(0)
摘要: 网址:https://www.crcv.ucf.edu/data/UCF101.php There will be a workshop in ICCV'13 with UCF101 as its main competition benchmark: The First International 阅读全文
posted @ 2020-02-18 09:38 LifeExp 阅读(1406) 评论(0) 推荐(0)
摘要: 命令行的方式: ipynb转换为pythonjupyter nbconvert --to python my_file.ipynbipynb转换为mdjupyter nbconvert --to md my_file.ipynbipynb转为htmljupyter nbconvert --to ht 阅读全文
posted @ 2020-01-17 21:11 LifeExp 阅读(866) 评论(0) 推荐(0)
摘要: 用windows系统的rar软件压缩的zip文档,在linux环境下格式不支持,linux用unzip出现了错误“unsupported compression method”。 网上说用7z,然而我没有管理员权限。 所以在windows下用了命令行里的tar命令打包成.tar.gz的格式,然后传到 阅读全文
posted @ 2020-01-17 20:23 LifeExp 阅读(1903) 评论(0) 推荐(0)