<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[Newt_Scamander的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/Newt_Scamander</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; Newt_Scamander]]></copyright><item><title><![CDATA[解决Python运行时qt.qpa.plugin: Could not find the Qt platform plugin “windows“ in问题]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/130824728</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/130824728</guid><author>Newt_Scamander</author><pubDate>Tue, 23 May 2023 12:36:29 +0800</pubDate><description><![CDATA[更新conda后运行python可能遇到qt.qpa.plugin: Could not find the Qt platform plugin "windows" in “”问题，是因为Qt不存在或者环境变量中没有设置。注意路径是D:\Anaconda\Library\plugins\platforms，不是在site-packges中的PyQt5中的plugins\platforms。或者在环境变量中设置上述路径。]]></description><category></category></item><item><title><![CDATA[《python基础教程第3版》笔记——对象和魔法(6到9章)]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122491390</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122491390</guid><author>Newt_Scamander</author><pubDate>Sat, 15 Jan 2022 10:13:08 +0800</pubDate><description><![CDATA[1
函数说明：在函数中写一个字符串说明，用__doc__属性访问
def cal(x):
    'Calculate the square of x'
    return x * x
print(cal.__doc__)

2
列表作为参数传入函数时会改变列表中的值，类似指针，需要采用深拷贝确保原始列表不会改变。可以采用切片的方法,如n = name[:]，这样n能获得name的全部值且地址不同。字典也会改变，只要是可改变的数据类型一般都会改变，元组和数不会改变。
3
‘zhao ming xu’.sp]]></description><category></category></item><item><title><![CDATA[train.py部分]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122271308</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122271308</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 21:42:08 +0800</pubDate><description><![CDATA[plots = not evolve  # create plots
    cuda = device.type != 'cpu'
    init_seeds(1 + RANK)
    with torch_distributed_zero_first(LOCAL_RANK):
        data_dict = data_dict or check_dataset(data)  # check if None
        这里的check_dataset会把train,val生成为p...]]></description><category></category></item><item><title><![CDATA[utils.general详解1]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122270393</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122270393</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 20:10:04 +0800</pubDate><description><![CDATA[class WorkingDirectory(contextlib.ContextDecorator): # 改变函数的工作路径
    # Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager
    def __init__(self, new_dir):
        self.dir = new_dir  # new dir
        self.cwd = Path.c]]></description><category></category></item><item><title><![CDATA[ModelEMA——滑动平均]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122268929</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122268929</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 17:16:42 +0800</pubDate><description><![CDATA[class ModelEMA:
    """ Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
    Keep a moving average of everything in the model state_dict (parameters and buffers).
    This is intended to allow functionality like
    h]]></description><category></category></item><item><title><![CDATA[callbacks&loggers]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122268407</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122268407</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 16:20:05 +0800</pubDate><description><![CDATA[if RANK in [-1, 0]:
        loggers = Loggers(save_dir, weights, opt, hyp, LOGGER)  # loggers instance
        if loggers.wandb:
            data_dict = loggers.wandb.data_dict
            if resume:
                weights, epochs, hyp = opt.weights, opt.]]></description><category></category></item><item><title><![CDATA[yolov5中的targets和imgs]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122268272</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122268272</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 16:04:25 +0800</pubDate><description><![CDATA[imgs.shape :torch.Size([4, 3, 640, 640])
targets.shape:torch.Size([9, 6])
targets:
tensor([[0.00000, 0.00000, 0.33555, 0.46680, 0.03516, 0.02734],
[1.00000, 0.00000, 0.46797, 0.54727, 0.03594, 0.02891],
[2.00000, 0.00000, 0.64336, 0.55273, 0.06641, 0.02734]]></description><category></category></item><item><title><![CDATA[yolo中锚框问题]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122266092</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122266092</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 11:16:22 +0800</pubDate><description><![CDATA[anchors:

[10,13, 16,30, 33,23]  # P3/8
[30,61, 62,45, 59,119]  # P4/16
[116,90, 156,198, 373,326]  # P5/32
这里的每一行代表一个尺度下的三个锚框，比如第一行是stride=8时的三个锚框，分别为1013，1630，33*23时比较适合检测小目标的尺度。


...]]></description><category></category></item><item><title><![CDATA[yolov5的问题总结]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122265984</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122265984</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 11:08:10 +0800</pubDate><description><![CDATA[yolo.py

一般前向推理时常用的还是forward_once就可以
Detect中的stride可以理解为网格的大小，例如取输入为[4,3,640,640]则根据anchors的大小计算出stride为[8,16,32],则输出为[4,3,80,80,85],[4,3,40,40,85],[4,3,20,20,85]。80*8=640,40*16=640,20*32=640。

class Model(nn.Module):
    def __init__(self, cfg='yolov5s.ya]]></description><category></category></item><item><title><![CDATA[yolov5网络结构分析]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122265743</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/122265743</guid><author>Newt_Scamander</author><pubDate>Sat, 01 Jan 2022 10:42:09 +0800</pubDate><description><![CDATA[yolov5s的网络结构简析]]></description><category></category></item><item><title><![CDATA[Matlab基础学习——矩阵和画图1]]></title><link>https://blog.youkuaiyun.com/Newt_Scamander/article/details/121755967</link><guid>https://blog.youkuaiyun.com/Newt_Scamander/article/details/121755967</guid><author>Newt_Scamander</author><pubDate>Mon, 06 Dec 2021 21:03:18 +0800</pubDate><description><![CDATA[Matlab基础学习——矩阵和画图1
% ini=imread('E:\G2\data\images_test_A\image000000.jpg');
% inigray = rgb2gray(ini);
% img = fftshift(fft2(inigray));
% imshow(img);
n = 2^10;                 % size of mask
M = zeros(n);
I = 1:n; 
x = I-n/2;                % mask x-coor]]></description><category></category></item></channel></rss>