星星的孩子X-CSDN博客

原创图文介绍RNN注意力机制

图文介绍RNN注意力机制 | PLM's Notes | 好好学习，天天笔记

2022-01-28 21:15:19 1255 1

""" 功能：测试gensim使用，处理中文语料 """ from gensim.models import word2vec import logging from gensim.models import Word2Vec from seaborn import heatmap from matplotlib import pyplot import numpy as np # 主程序 logging.basicConfig(format='%(asctime)s : %(levelname)s..

2022-01-25 20:26:47 1433

原创自己实现word2vec

import numpy as np import torch import torch.nn as nn import torch.optim as optim from torch.autograd import Variable import matplotlib.pyplot as plt from gensim.models import word2vec dtype = torch.FloatTensor # 3 Words Sentence # 分词，词汇表构造以及词汇索引的构造 sent.

2022-01-25 20:24:41 270

原创 VGG16_GPU

import torch import torch.nn as nn import torchvision.models as models import matplotlib.pyplot as plt import torchvision.datasets import torchvision.transforms as transforms from collections.abc import Iterable # 检测是否可以使用GPU from torch.utils.data import .

2022-01-24 19:56:37 465

原创 VGG16_cpu

import torch import torch.nn as nn import torchvision.models as models import matplotlib.pyplot as plt import torchvision.datasets import torchvision.transforms as transforms from collections.abc import Iterable # 检测是否可以使用GPU from torch.utils.data import .

2022-01-24 19:56:02 772

原创自己实现resnet18网络结构

import torch import torch.nn as nn # 定义一个Residual模块 class Residual(nn.Module): def __init__(self,in_channels,out_channels,stride=1): super(Residual, self).__init__() self.stride = stride self.conv1 = nn.Conv2d(in_channels,out..

2022-01-24 19:54:57 897

原创 GPU实现

import torch import torchvision.datasets from matplotlib import pyplot as plt from torch.utils.data import DataLoader from torchvision.transforms import transforms import torch.nn as nn import os os.environ['KMP_DUPLICATE_LIB_OK'] = 'True' # 调用torchvis.

2022-01-24 19:53:42 152

原创调用TorchVision中训练好的ResNet网络训练CIFAR10

import torch import torchvision.datasets from matplotlib import pyplot as plt from torch.utils.data import DataLoader from torchvision.transforms import transforms import torch.nn as nn import imutils # 调用torchvision中的models中的resnet网络结构 import torchvisi.

2022-01-24 19:52:27 3732 1

原创 CIFAR10_ResNet

import torch import torchvision.datasets from matplotlib import pyplot as plt from torch.utils.data import DataLoader from torchvision.transforms import transforms import torch.nn as nn import os os.environ['KMP_DUPLICATE_LIB_OK'] = 'True' # 调用torchvis.

2022-01-24 19:50:38 809 1

原创 ResNet

# 调整已经训练好的ResNet网络 class ResNet(nn.Module): def __init__(self, num_classes=10): # num_classes，此处为二分类值为2 super(ResNet, self).__init__() net = models.resnet18(pretrained=True) # 从预训练模型加载resnet18网络参数 net.classifier = nn.Sequen.

2022-01-24 19:49:41 2450

原创 CIFAR10

import torch.optim from torch.utils.tensorboard import SummaryWriter # from model import * # 注意model文件和train文件是在同一个目录底下 import torchvision.datasets from torch import nn import torchvision.transforms as transforms from torch.nn import * from torch.utils.

2022-01-24 19:46:04 379

原创不调用torch.nn中函数，自己实现cnn的功能进行mnist手写体识别

import torchvision.transforms from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter from torchvision import datasets import numpy as np import matplotlib.pyplot as plt # 1.导入mnist数据集 train_dataset = datasets.MNIST(root.

2022-01-24 19:44:12 568 1

原创 CNN实现mnist手写识别/CIFAR10数据集（PyTorch）

import torch import torch.nn as nn import torch.utils.data as Data import torchvision import matplotlib.pyplot as plt import os import cv2 from torchvision import transforms torch.manual_seed(1) # 使用随机化种子使神经网络的初始化每次都相同 # 超参数 EPOCH = 10 # 训练整批数据的次数 BAT.

2022-01-24 19:39:24 895

原创 OpenCV

图像的的基本操作去除图片噪音的几种方式如下：均值滤波方框滤波高斯滤波中值滤波(效果最好) candy进行边缘检测(其中用的是sobel算子) import cv2 as cv import numpy as np image = cv.imread("D:\APP\PycharmProjects\pythonProject\learn_opencv\images\sp_noise.png") # cv.imshow("image",image) # 均值滤波 # 简单的平均卷

2021-11-25 19:20:34 1242