1.常见的功能
nn.ReLU:小于0,归零
二分类输出层用sigmod,隐藏层用ReLu(弹幕上说的)
2.Relu的参数
(1)inplace 原地替换
3.Relu的构建
import torch
from torch import nn
data = torch.tensor([[1, 2, 3],
[2, 4, -10],
[-1, 2, -9]])
print(data)
class Relu(nn.Module):
def __init__(self):
super().__init__()
self.relu1 = nn.ReLU(inplace=False)
def forward(self, input):
output = self.relu1(input)
return output
Relu1 = Relu()
output = Relu1(data)
print(output)
输出结果
4.sigmoid处理图像
import torchvision.datasets
from torch import nn
from torch.nn import Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
# 数据集
dataset = torchvision.datasets.CIFAR10('../dataset', train=False, transform=torchvision.transforms.ToTensor(),
download=False)
dataloader = DataLoader(dataset, batch_size=10, shuffle=True)
class Sigmoid1(nn.Module):
def __init__(self):
super().__init__()
self.sigmoid = Sigmoid()
def forward(self, input):
output = self.sigmoid(input)
return output
writer = SummaryWriter('../Sigmoid')
Sigmoid_image = Sigmoid1()
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images('Input image', imgs, step)
output = Sigmoid_image(imgs)
writer.add_images('output image', output, step)
step = step + 1
writer.close()