- 博客(30)
- 资源 (1)
- 收藏
- 关注
RSS订阅原创 人脸检测,级联检测
import cv2face = cv2.CascadeClassifier(r'E:\net\haarcascade_frontalface_default.xml')video = cv2.VideoCapture(0) ##读取摄像头while video.isOpened(): if video.isOpened(): ret ,frame = video.read() frame = cv2.cvtColor(frame,cv2.COLOR_
2022-05-07 17:40:14
331
原创 opencv python 的基本操作案例（一） 记录，可查看
import cv2####图像的读取显示和写入：# cv2.IMREAD_COLOR：读入一副彩色图像。图像的透明度会被忽略，# 这是默认参数。# • cv2.IMREAD_GRAYSCALE：以灰度模式读入图像# cv2.IMREAD_UNCHANGED：读入一幅图像，并且包括图像的 alpha 通道# img = cv2.imread('d:/pictures/1.jpg',cv2.IMREAD_UNCHANGED) ###BGR读入# cv2.imshow("img",img
2022-05-06 22:34:24
1778
原创 mutex python
import threadingmutex = threading.Lock()num = 0def test1(temp): global num mutex.acquire() for i in range(temp): num +=1 print('test1',num) mutex.release() def test2(temp): global num mutex.acquire() for i in range(t
2022-05-05 20:49:43
504
原创 threading，python
import threadingimport timedef ford(): for i in range(10): print('dd') time.sleep(1)def fords(): for i in range(10): print('ddddd') time.sleep(1)def main(): t1 = threading.Thread(target = ford) t2 = threading.Thread(target =...
2022-05-05 18:51:31
430
原创 tcpsssss
import socket####服务器def main(): tcps = socket.socket(socket.AF_INET , socket.SOCK_STREAM) tcps.bind(('192.168.248.128',8082)) #########Connect tcps.listen(128) while True: a,b = tcps.accept() d = a.recv(1024).decode('utf-8'...
2022-05-05 17:55:56
52
原创 udp python tcp server
import socketdef main(): s= socket.socket(socket.AF_INET , socket.SOCK_DGRAM) #ipv4 ,udp # print(s) s.sendto(b'hhafjskfjkasjfhasjkfhjks',("192.168.43.237",8080)) # s.close()if __name__ == '__main__': main()``111`import sock.
2022-05-05 14:33:44
1566
1
原创 dataset读取方式二
import torchvision.datasets as datasetsfrom torchvision import transforms,utilsfrom torch.utils.data import dataloader,DataLoadertrans = transforms.Compose([transforms.ToTensor(),transforms.Resize((48,48))])data = datasets.ImageFolder(root=r'E:\pyth
2022-05-04 21:03:45
93
原创 dataset图像加载和显示
在这里插入代码################dataset1111111#########################import torchimport osfrom torch.utils.data import Dataset ,DataLoaderfrom torch import nn as nnfrom torchvision import transformsimport numpy as npfrom PIL import Imageimport cv2c
2022-05-04 20:39:01
226
原创 dataset数据集读取 ----1
class Mydataset(Dataset): def __init__(self,fliepatch ,lablespatch ,transfrom =None ): self.trans = transfrom self.images = [] self.classes = [] subist= os.listdir(fliepatch) for i in subist: self.
2022-05-04 16:35:56
498
原创 numpy基本操作例子，cmd操作，有需要看正确的示例
Microsoft Windows [版本 10.0.19043.1645](c) Microsoft Corporation。保留所有权利。C:\Users\ymd>pythonPython 3.8.5 (default, Sep 3 2020, 21:29:08) [MSC v.1916 64 bit (AMD64)] :: Anaconda, Inc. on win32Warning:This Python interpreter is in a conda environmen
2022-05-04 13:41:35
832
原创 tensorflow，训练过程代码。使用fashionmnist为例子
import tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras import datasets,Sequential ,layers,metrics, optimizers(x,y),(x_test,y_test) = datasets.fashion_mnist.load_data()def processing(x, y): x = tf.cast(x,dtype = tf.floa
2022-04-18 20:45:44
204
原创 ModuleNotFoundError: No module named ‘keras.api‘解决
重点在于import tensorflow.keras (可行)我在 cmd 和notebook都试了cmd的： ^SyntaxError: invalid syntax>>> import tensorflow as tf2022-04-12 15:12:12.866276: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic libr
2022-04-12 15:26:03
10824
3
原创 torch.cat()函数 dim = 2 和 -1 时关于第三维度的拼接。不理解的可问
import torchc = torch.randn((2,3,4))d = torch.randn((2,3,4))print(c,d)print(c.shape,d.shape)print(torch.cat((c,d),dim=0))print(torch.cat((c,d),dim=1))print(torch.cat((c,d),dim=2))m = torch.cat((c,d),dim=0)n = torch.cat((c,d),dim=1)l = torch.cat(
2022-03-29 14:39:07
3845
1
原创 vgg-16自复现
```pythonimport torchimport torch.nn as nnimport torch.nn.functional as Fclass conv1(nn.Module): def __init__(self , inchannel ,outchannel): super(conv1, self).__init__() self.conv1 = nn.Sequential( nn.Conv2d(in_cha.
2022-03-13 18:33:20
156
原创 inception-v1 自复现 有问题尽管问
代码：import torchimport torch.nn as nnimport torch.nn.functional as Fclass inceptionModuleV1(nn.Module): def __init__(self,inputs, outputs1 , outputs2 ,outputs3 ,outputs4 ,outputs5 ,outputs6): super(inceptionModuleV1,self).__init__()
2022-03-13 10:30:01
82
原创 自复现的alexnet模型，学习记录，有疑问请指出
```pythonimport torchimport torch.nn as nnimport torch.nn.functional as Fclass ALX(nn.Module): def __init__(self): self.conv1 = nn.Conv2d(in_channels=3 ,out_channels= 96 ,kernel_size= 11 ,stride= 4 ,padding= 0) self.maxpool =.
2022-03-10 18:40:19
157
原创 numpy 数组乘法，加法
两个数组 a 和 b 形状相同，即满足 a.shape == b.shape，那么 a*b 的结果就是 a 与 b 数组对应位相乘，相加，当维度不同时，广播机制import numpy as npa = np.array([[0,1,2,3],[1,1,2,3],[2,1,2,3],[3,1,2,3]])b = np.array([0,1,2,3])c = np.array([[0,1,2,3]])print(a+ b)print(a+c)结果[[0 2 4 6][1 2 4 6]
2022-03-08 14:25:48
1362
原创 AI-openpose，肢体识别，预训练模型，mobilenet_sgd_68.848.pth.tar
我就不上传csdn了，下载需要花钱。有需要的可以私信我。
2022-03-03 10:16:46
609
43
原创 Rnn ，沐神
这里 我就直接上代码了 ，因为沐神的是分开的 ，我调试放到了一起，`import torchimport randomimport zipfilefrom acem.utils import *device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')print(torch.__version__)print(device)## with zipfile.ZipFile('./jaychou_lyrics.t
2021-11-30 19:31:59
163
原创 2021-10-18
import torchx_da = [1.0,2.0,3.0]y_da = [2.0,4.0,6.0]w = torch.Tensor([1.0])w.requires_grad = Truedef forward(x): return w * xdef loss(x , y): return (forward(x) - y)**2epoc = []costs = []for epo in range(100): for xs, ys in z..
2021-10-18 16:01:22
79
原创 mnist识别模型生成，加识别代码。
import torchfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as F #reluimport torch.optim as optimbatch_size = 64transform = transforms.Compose([transforms.ToTen
2021-10-15 23:28:50
92
原创 多特征降维 pytorch刘二 ，多参数变化
import numpy as npimport torchxy = np.loadtxt(r"d:\diabetes.csv.gz",delimiter=',',dtype=np.float32)x_data = torch.from_numpy(xy[:,:-1])y_data = torch.from_numpy(xy[:,[-1]])class MoreModel(torch.nn.Module): def __init__(self): super(More
2021-10-14 15:34:09
245
2
原创 pytorch Tensor和tensor张量变换差异----Found dtype Long but expected Float：刘二
import torchx_data = torch.tensor([[1.0],[2.0],[3.0]])y_data = torch.tensor([[5.0],[6.0],[7.0]])class LinerModel(torch.nn.Module): def __init__(self): super(LinerModel,self).__init__() self.lin = torch.nn.Linear(1,1) def fo
2021-10-14 13:53:40
461
原创 pytorch线性模型 刘二
代码如下：import torchx_data = torch.tensor([[1.0],[2.0],[3.0]])y_data = torch.tensor([[2.0],[4.0],[6.0]])class Linear(torch .nn.Module): def __init__(self): super(Linear,self).__init__() self.linear = torch.nn.Linear(1,1)
2021-10-14 00:20:39
60
原创 2021-10-13
cnn fer2013识别：直接上代码，经过学习网上的一下大佬的修改后import torchimport torch.utils.data as dataimport torch.nn as nnimport torch.optim as optimimport numpy as npimport pandas as pdimport cv2import h5pydef gaussian_weights_init(m):classname = m.class.name# 字符串查找
2021-10-13 09:49:01
136
原创 2021-10-13
PyTorch反向传播学习实例（p4）刘二import torchx_da = [1.0,2.0,3.0]y_da = [2.0,4.0,6.0]w1 = torch.tensor([1.0])w1.requires_grad= Truew2= torch.tensor([1.0])w2.requires_grad=Trueb = torch.tensor([1.0])b.requires_grad=Truedef dors(x): return w1 *x *x + w
2021-10-13 09:43:36
68
1
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人