weixin_43328054的博客

import torch from torch import nn class VAE(nn.Module): def __init__(self): super().__init__() self.encoder = nn.Sequential( nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 64), nn.ReLU(),

import torch from torch import nn class AE(nn.Module): def __init__(self): super().__init__() self.encoder = nn.Sequential( nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 64), nn.ReLU(),

import torch import torchvision from PIL import Image from torch import nn image_path = "./imgs/dog.jpeg" image = Image.open(image_path) # 图片保留三通道 image = image.convert('RGB') transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32

GPU使用1 import torch import torchvision.datasets from torch.utils.tensorboard import SummaryWriter import time # 准备数据集 from torch import nn from torch.utils.data import DataLoader import nn_seq train_data = torchvision.datasets.CIFAR10(root="../dataset"

import torch import torchvision.datasets from torch.utils.tensorboard import SummaryWriter from MyModule import * # 准备数据集 from torch import nn from torch.utils.data import DataLoader import nn_seq train_data = torchvision.datasets.CIFAR10(root="./datas

保存 import torch import torchvision vgg16 = torchvision.models.vgg16(pretrained=False) # 保存方式1 保存模型结构 + 模型参数 torch.save(vgg16, "vgg16_method1.pth") # 保存方式2 保存模型参数（官方推荐） torch.save(vgg16.state_dict(), "vgg16_method2.pth") 加载 import torch import torchvi

import torchvision from torch import nn vgg_false = torchvision.models.vgg16(pretrained=False) # 参数使用在别的数据集上训练好的初始化 vgg_true = torchvision.models.vgg16(pretrained=True) # 在现有的网络结构进行一些修改，使它适用于自己的网络结构 train_data = torchvision.datasets.CIFAR10("./dataset",

import torch from torch import nn import torchvision from torch.nn import Conv2d, MaxPool2d, ReLU, Linear, Flatten from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter dataset = torchvision.datasets.CIFAR10("./dataset

import torch from torch.nn import L1Loss, MSELoss, CrossEntropyLoss inputs = torch.tensor([1, 2, 3], dtype=torch.float32) targets = torch.tensor([1, 2, 5], dtype=torch.float32) inputs = torch.reshape(inputs, (1, 1, 1, 3)) targets = torch.reshape(targets,

不使用Sequential import torch from torch import nn import torchvision from torch.nn import Conv2d, MaxPool2d, ReLU, Linear, Flatten from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter class MyModule(nn.Module): de

import torch from torch import nn import torchvision from torch.nn import Conv2d, MaxPool2d, ReLU, Linear from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter dataset = torchvision.datasets.CIFAR10("./dataset", train=

import torch from torch import nn import torchvision from torch.nn import Conv2d, MaxPool2d, ReLU from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter input = torch.tensor([[1, -0.5], [-1, 3]]) in

import torch from torch import nn import torchvision from torch.nn import Conv2d, MaxPool2d from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter dataset = torchvision.datasets.CIFAR10("../dataset", train=False, transf

import torch from torch import nn import torchvision from torch.nn import Conv2d from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter dataset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvisi

import torch from torch import nn class MyModule(nn.Module): def __init__(self) -> None: super().__init__() def forward(self, input): output = input + 1 return output moudle = MyModule() x = torch.tensor(1.0) o

import torchvision from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter # 准备测试集 test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor()) # batch_size为批量大小（即每次取四张图片

import torchvision from torch.utils.tensorboard import SummaryWriter dataset_transform = torchvision.transforms.Compose([ torchvision.transforms.ToTensor() ]) train_set = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=dataset_tr

from PIL import Image from torchvision import transforms from torch.utils.tensorboard import SummaryWriter img = Image.open("/Users/computer/Documents/Code/pytorchLearning/imgs/five.png") trans_toTensor = transforms.ToTensor() tran_img = trans_toTensor(im

from PIL import Image from torchvision import transforms from torch.utils.tensorboard import SummaryWriter import cv2 writer = SummaryWriter("logs") # 1. transforms如何使用 img_path = "dataset/train/ants/0013035.jpg" img = Image.open(img_path) # 创建对象 tensor

from torch.utils.tensorboard import SummaryWriter from PIL import Image import numpy as np writer = SummaryWriter("logs") img_path = "dataset/train/ants/0013035.jpg" img_PIL = Image.open(img_path) img_array = np.array(img_PIL) print(type(img_array)) # 输出