Pytorch训练可视化(TensorboardX)

深度学习与Pytorch入门实战（七）Visdom可视化工具【数字识别实例】

https://www.cnblogs.com/douzujun/p/13324435.html

【深度学习-pytorch-番外篇】如何使用Tensorboard可视化Pytorch训练结果

https://blog.csdn.net/Kefenggewu_/article/details/118292747?spm=1001.2101.3001.6661.1&utm_medium=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_aa&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_aa&utm_relevant_index=1

https://zhuanlan.zhihu.com/p/54947519

[官方总结] tensorboardX 使用教程

https://blog.csdn.net/qq_39575835/article/details/89160828

torch.nn.conv3d理解

https://blog.csdn.net/weixin_42769131/article/details/104826953

支持PyTorch的einops张量操作神器用法示例详解

https://www.jb51.net/article/226979.htm

https://www.cnblogs.com/c-chenbin/p/15375637.html

详解PyTorch中的ModuleList和Sequential

https://zhuanlan.zhihu.com/p/75206669

Pytorch tf.nn.functional.softmax(x,dim = -1)对参数dim的理解

https://blog.csdn.net/weixin_44317740/article/details/107373202

Numpy中transpose()函数的可视化理解

https://zhuanlan.zhihu.com/p/61203757

对pytorch中x = x.view(x.size(0), -1) 的理解说明

https://www.jb51.net/article/206748.htm

https://mapengsen.blog.csdn.net/article/details/115214078

Python3.x：python: extend (扩展) 与 append (追加) 的区别

https://www.cnblogs.com/lizm166/p/8232733.html

nn.linear()函数

https://blog.csdn.net/daydaydreamer/article/details/102638624

torch.nn.Embedding()函数解读

https://blog.csdn.net/qq_40178291/article/details/100658867

pytorch LayerNorm参数的用法及计算过程

https://www.jb51.net/article/213383.htm

nn.LayerNorm的参数

https://blog.csdn.net/qq_45893319/article/details/122327931

Pytorch数据预处理：transforms的使用方法

https://zhuanlan.zhihu.com/p/130985895

transforms.Resize(256)是按照比例把图像最小的一个边长放缩到256，另一边按照相同比例放缩。
transforms.RandomResizedCrop(224,scale=(0.5,1.0))是把图像按照中心随机切割成224正方形大小的图片。

# transforms.Resize([h, w])

pytorch torch.manual_seed()用法

https://www.cnblogs.com/dychen/p/13920000.html

normal_kernel_cpu“ not implemented for ‘Long‘

https://blog.csdn.net/YUwoshijiantian/article/details/115219686

在0后面加个 .

pytorch读取本地的mnist数据集【实测成功】

https://blog.csdn.net/weixin_41529093/article/details/111354381?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&utm_relevant_index=2

需要导入：import gzip ，取消类名括号内的参数

Pytorch MNIST直接离线加载二进制文件到pytorch

https://blog.csdn.net/caomin1hao/article/details/108522205

pytorch-构建自己的dataset类

https://blog.csdn.net/l641208111/article/details/113838584

https://zhuanlan.zhihu.com/p/159484351

https://www.jianshu.com/p/4818a1a4b5bd

https://www.cnblogs.com/popodynasty/p/15170266.html

https://blog.csdn.net/zw__chen/article/details/82806900

https://blog.csdn.net/sinat_42239797/article/details/90641659?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&utm_relevant_index=2

https://blog.csdn.net/qq_34107425/article/details/104097402?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&utm_relevant_index=2

pytorch如何显示数据图像，以及标签。TypeError: img should be PIL Image. Got ＜class ‘numpy.ndarray‘＞

所以我们要在转换中先转换为PIL格式。
transforms.ToPILImage()

https://blog.csdn.net/wacebb/article/details/108003306

https://blog.csdn.net/qq_40178291/article/details/101108327

PIL.JpegImagePlugin.JpegImageFile与numpy.ndarray的相互转换

https://blog.csdn.net/hua_you_qiang/article/details/118683134?utm_medium=distribute.pc_aggpage_search_result.none-task-blog-2~aggregatepage~first_rank_ecpm_v1~rank_v31_ecpm-1-118683134.pc_agg_new_rank&utm_term=ndarray%E8%BD%ACjpegimagefile&spm=1000.2123.3001.4430

np.ndarray与torch.Tensor之间的转化（图像的区别）

https://blog.csdn.net/weixin_45508265/article/details/119040774?utm_medium=distribute.pc_relevant.none-task-blog-2~default~baidujs_title~default-0.pc_relevant_default&spm=1001.2101.3001.4242.1&utm_relevant_index=3

【学习笔记】pytorch中squeeze()和unsqueeze()函数介绍

https://blog.csdn.net/flysky_jay/article/details/81607289

高版本pytorch出现IndexError: invalid index of a 0-dim tensor.问题解决办法

https://blog.csdn.net/qq_31511955/article/details/111829976?spm=1001.2101.3001.6661.1&utm_medium=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&utm_relevant_index=1

NameError:name ‘xrange’ is not defined

https://www.cnblogs.com/hdk1993/p/8893991.html

PyTorch:expected scalar type Float but found Double

https://chenlinwei.blog.csdn.net/article/details/109725458?spm=1001.2101.3001.6661.1&utm_medium=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_paycolumn_v3&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_paycolumn_v3&utm_relevant_index=1

这个问题很明显就是网络内的参数类型不同；
修改：
在前面添加：
torch.set_default_tensor_type(torch.DoubleTensor)
或者，在运行网络前添加：
net = net.double()

https://blog.csdn.net/weixin_41514525/article/details/110129655

多GPU训练相关问题

pytorch错误：Missing key(s) in state_dict、Unexpected key(s) in state_dict解决

https://www.cnblogs.com/zhengbiqing/p/10434704.html

Missing key(s) in state_dict: “module.features.0.0.weight

https://blog.csdn.net/qq_35037684/article/details/115109416

[python][pytorch]多GPU下的模型保存与加载

https://www.cnblogs.com/wildkid1024/p/13025352.html

https://github.com/bearpaw/pytorch-classification/issues/27

【Pytorch多GPU训练错误】AttributeError: ‘DataParallel’ object has no attribute ‘xxxx

https://blog.csdn.net/weixin_41990278/article/details/105127101

【PyTorch问题】can‘t convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy...略

https://blog.csdn.net/xiaoxiao_ziteng/article/details/115432973?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.topblog&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.topblog&utm_relevant_index=2

https://blog.csdn.net/wacebb/article/details/114652811

在我们想把 GPU tensor 转换成 Numpy 变量的时候，需要先将 tensor 转换到 CPU 去，因为 Numpy 是 CPU-only 的。

训练模型的时候， Warning: NaN or Inf found in input tensor 解决办法

https://blog.csdn.net/qq_38284961/article/details/102935800

https://blog.csdn.net/JSLS_Hf/article/details/81743045?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_paycolumn_v3&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_paycolumn_v3&utm_relevant_index=2

https://blog.csdn.net/weixin_41278720/article/details/80778640?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_paycolumn_v3&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_paycolumn_v3&utm_relevant_index=2

Detected call of `lr_scheduler.step()` before `optimizer.step()`.

https://blog.csdn.net/weixin_38314865/article/details/103937717

https://blog.csdn.net/qq_41166909/article/details/122531321?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromBaidu%7EHighlightScore-1.queryctrv2&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromBaidu%7EHighlightScore-1.queryctrv2&utm_relevant_index=2

应该把lr_scheduler.step()放在每次epoch训练完成之后

https://zhuanlan.zhihu.com/p/136902153

model.train()与model.eval()的用法

https://www.cnblogs.com/elitphil/p/15532447.html

https://blog.csdn.net/kking_edc/article/details/104663305

model.train():

在使用pytorch构建神经网络的时候，训练过程中会在程序上方添加一句model.train()，作用是启用batch normalization和drop out。
model.eval():
测试过程中会使用model.eval()，这时神经网络会沿用batch normalization的值，并不使用drop out。

pycharm代码块左移、右移

在使用pycharm编写代码时，会遇到代码块左移右移的操作
1.代码快右移：选中多行代码，tab键缩进，一次缩进4个字符
2.代码块左移：选中多行代码，shift+tab，一次左移4个字符

Pytorch-对于pytorch下载CIFAR10数据集很慢或卡住的解决方法

https://blog.csdn.net/qq_28790663/article/details/115032503

Ubuntu16.04下Python程序出现错误qt.qpa.plugin: Could not load the Qt platform plugin xcb解决方法

https://blog.csdn.net/zhanghm1995/article/details/106474505

https://www.jb51.net/article/193024.htm

https://blog.csdn.net/agonysome/article/details/108985079

QObject::moveToThread: Current thread(...) is not the object`s thread. Cannot move to target thread(

https://chowdera.com/2022/02/202202100555216474.html

https://blog.csdn.net/qq_29750461/article/details/109720034?spm=1001.2101.3001.6650.9&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-9.pc_relevant_paycolumn_v3&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-9.pc_relevant_paycolumn_v3&utm_relevant_index=12

https://blog.csdn.net/weixin_42326323/article/details/99309231?spm=1001.2101.3001.6650.3&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromBaidu%7EHighlightScore-3.queryctrv2&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromBaidu%7EHighlightScore-3.queryctrv2&utm_relevant_index=6

https://blog.csdn.net/weixin_38082364/article/details/89234765

Pytorch-18种经典的损失函数

https://blog.csdn.net/weixin_43687366/article/details/107927693

https://www.jianshu.com/p/4812f381a24a

https://blog.csdn.net/tototuzuoquan/article/details/113777788

python批量将视频转化为图片

https://www.cnblogs.com/stupidwf/p/13338218.html

https://www.pythonheidong.com/blog/article/1163380/3df3c70fa0d484c62dd4/

CV2逐步学习-1.imread()详解+cvtColor()颜色空间转换

https://blog.csdn.net/sunjintaoxxx/article/details/121262553

img=cv2.imread('aima.jpg')
img_rgb=cv2.cvtColor(img,cv2.COLOR_BGR2RGB)

Softmax函数和Sigmoid函数的区别与联系

https://zhuanlan.zhihu.com/p/356976844

EMD(earth mover's distances)距离

https://zhuanlan.zhihu.com/p/145739750

【pytorch系列】 with torch.no_grad():用法详解

https://blog.csdn.net/sazass/article/details/116668755

pandas to_csv() 索引列表第一行是0的问题

https://blog.csdn.net/Ly_Word/article/details/116152644

pandas中Dataframe选取指定行和列或删除含有指定数值的行或者列

https://blog.csdn.net/wf592523813/article/details/96278289

数据框DataFrame和列表List相互转换

https://www.cnblogs.com/xiaodangdang/p/12098137.html

json转化为dataframe 和dataframe转化为json

https://blog.csdn.net/sslfk/article/details/122824057?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-1.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-1.pc_relevant_default&utm_relevant_index=2

Python3 * 和 ** 运算符

https://blog.csdn.net/yilovexing/article/details/80577510

python中 // 和 / 和 %

https://blog.csdn.net/qq_29566629/article/details/95374971?spm=1001.2101.3001.6661.1&utm_medium=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_aa&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_aa&utm_relevant_index=1

“/”，这是传统的除法，3/2=1.5
“//”，在python中，这个叫“地板除”，3//2=1
“%”，这个是取模操作，也就是区余数，4%2=0，5%2=1

序列解包

https://blog.csdn.net/yilovexing/article/details/80576788

python内置函数：enumerate用法总结

https://blog.csdn.net/IAMoldpan/article/details/78487809

enumerate(iterable, start=0)
第一个参数为可迭代的数据，比如python中的list。第二个参数为该函数打印标号的初始值，默认从0开始打印，该函数返回一个enumerate类型的数据。

*args 和 **kwargs 主要用于函数定义。

https://blog.csdn.net/yilovexing/article/details/80577510

*args 与 **kwargs 的区别，两者都是 python 中的可变参数：
*args 表示任何多个无名参数，它本质是一个 tuple
**kwargs 表示关键字参数，它本质上是一个 dict
如果同时使用 *args 和 **kwargs 时，必须 *args 参数列要在 **kwargs 之前。

python -- 定义函数 def 后面的 -＞，：表示的含义

https://blog.csdn.net/qq_40913465/article/details/108407867

设置python搜索路径的几种方法

https://blog.csdn.net/phy12321/article/details/104137387?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-1.pc_relevant_default&utm_relevant_index=2

python临时添加当前工作路径

export PYTHONPATH=$PYTHONPATH:./
这样找模块就方便多了

python之parser.add_argument()用法——命令行选项、参数和子命令解析器

https://blog.csdn.net/qq_34243930/article/details/106517985

【Python】python中argparse.add_argument中的action=‘store_true‘使用总结

https://blog.csdn.net/AugustMe/article/details/109593110

AttributeError: module 'cv2.cv2' has no attribute 'DualTVL1OpticalFlow_create'

https://www.codeleading.com/article/21272688801/

opencv4.0以下版本API接口“cv2.DualTVL1OpticalFlow_create()”，opencv4.0以上版本API接口使用“cv2.optflow.DualTVL1OpticalFlow_create()

pip install opencv_python==4.1.2.30

pip install opencv-contrib-python==4.1.2.30

AttributeError: module 'cv2.optflow' has no attribute 'DISOpticalFlow_create'

https://answers.opencv.org/question/212935/disoptical-flow-in-41/

# 3.4.4.19
    #inst = cv2.optflow.createOptFlow_DIS(cv2.optflow.DISOPTICAL_FLOW_PRESET_MEDIUM)
# 4.1
    inst = cv2.DISOpticalFlow_create(cv2.DISOPTICAL_FLOW_PRESET_MEDIUM)

AttributeError: module 'cv2.optflow' has no attribute 'DISOpticalFlow_create'

Legacy autograd function with non-static forward method is deprecated.

https://zhuanlan.zhihu.com/p/355875710

记录自己调试SSD过程(第一次写，如有不对，请各位指正)

https://www.icode9.com/content-4-1021875.html

https://www.pythonheidong.com/blog/article/1412072/eb89ccea2f26626bda76/

https://blog.csdn.net/jacke121/article/details/116549423

ValueError: threshold must be numeric and non-NAN, try sys.maxsize for untruncated representation

https://blog.csdn.net/weixin_45752264/article/details/123406374

ModuleNotFoundError：No module named ‘pycocotools‘的解决办法汇总

https://blog.csdn.net/qq_42672745/article/details/116358111

pip install pycocotools-windows

Python数据预处理之数据规范化

https://blog.csdn.net/weixin_46599926/article/details/123888199

error: ‘constexpr’ needed for in-class initialization of static data member ‘const double sba::Con2d

https://blog.csdn.net/wphkadn/article/details/88174109

const static 和 static const一样，都不能在类内直接初始化非整形常量，可以修饰int，bool，char，但不能修饰其他类型（如double，float）
在c++11中，可以使用 constexpr static 或者 static constexpr 来修饰非整形静态成员常量。
也就是说，上面这一行出错的代码要改成
constexpr static double qScale = 1.0;
//或者 static constexpr double qScale = 1.0;

发表于 2022-02-06 11:49 funykatebird 阅读(965) 评论(0) 编辑收藏举报

会员力量，点亮园子希望

刷新页面返回顶部

Pytorch训练可视化(TensorboardX)

公告