Thumb_的博客

import torchfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport torch.optim as optimbatch_size = 64transform = transforms.Compose([ transforms.ToTensor()

import numpy as npimport torchfrom torch.utils.data import Datasetfrom torch.utils.data import DataLoader## prepare datasetclass DiabetesDataset(Dataset): def __init__(self, filepath): xy = np.loadtxt(filepath, delimiter=',', dtype=np.flo

import numpy as npimport torchxy = np.loadtxt('E:/BaiduNetdiskDownload/PyTorch深度学习实践/diabetes.csv.gz', delimiter=',', dtype=np.float32)x_data = torch.from_numpy(xy[:, :-1])y_data = torch.from_numpy(xy[:, [-1]])class Model(torch.nn.Mod

import torchimport matplotlib.pyplot as plt## prepare datasetx_data = torch.Tensor([[1.0], [2.0], [3.0]])y_data = torch.Tensor([[2.0], [4.0], [6.0]])## design model using classclass LinearModel(torch.nn.Module): def __init__(self): supe

# 1. 加载数据集import torchimport torch.nn as nnimport torchvision.transforms as transformsimport torchvision.datasets as datasetsimport torchvisionimport numpy as npimport pandas as pdimport matplotlib.pyplot as plt# 2. 下载 mnist 数据集trainsets = dat

Tensor的算术运算——加法运算c = a + b c = torch.add(a,b)a.add(b)a.add_(b)其中，前三种一样，第四种是对 a 进行了修改。Tensor的算术运算——减法运算减法同理c = a - bc = torch.sub(a,b)a.sub(b)a.sub_(b)Tensor的算术运算——乘法运算哈达玛积（element wise,对应元素相乘）c = a * bc = torch.mul(a,b)a.mul(b)a.mul_(b)

张量的存放位置import torchdev = torch.device("cpu") # 将tensor放置在cpu上，用cpu进行计算a = torch.tensor([2,2]，evice=dev)print(a)输出：tensor([2, 2])dev = torch.device("cpu") # 将tensor放置在cpu上，用cpu进行计算dev = torch.device("cuda") # 存放在cuda上a = torch.tensor([2,2],

Tensor的属性Tensor的属性——稀疏的张量torch.sparse_coo_tensorcoo类型表示了非零元素的坐标形式indices = torch.tensor([[0,1,1],[2,0,2]]) # 非零元素的坐标（0，2），（1，0），（1，2）values = torch.tensor([3,4,5],dtype=torch.float32) # 对应非零元素的值3，4，5x = torch.sparse_coo_tensor(i,v,[2,4]) # 一个 2

import torcha = torch.Tensor([[1,2],[3,4]])print(a)print(a.type())a = torch.Tensor(2,3)print(a)print(a.type())'''几种特殊的tensor'''a = torch.ones(2,2) # 全 1 的 tensorprint(a)print(a.type())a = torch.eye(2,2) # 对角线是 1 的 tensorprint(a)prin