非线性激活

# 1.非线性激活
# inplace为原地替换，若为True，则变量的值被替换。若为False，则会创建一个新变量，将函数处理后的值赋值给新变量，原始变量的值没有修改。
# ReLU函数的数学表达式为f(x)=max(0,x)，意味着当输入x大于0时，输出就是输入本身；当输入小于或等于0时，输出为0。
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

input = torch.tensor([[1, -0.5],
                      [-1, 3]])
input = torch.reshape(input, (-1, 1, 2, 2))
print(input.shape)


class MyModule(nn.Module):
    def __init__(self):
        super(MyModule, self).__init__()
        self.relu = nn.ReLU()

    def forward(self, input):
        output = self.relu(input)
        return output


model = MyModule()
output = model(input)
print(output)

# tensorboard显示
dataset = torchvision.datasets.CIFAR10(root='D:\PyCharm\CIFAR10', train=False,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset=dataset, batch_size=64)


class MyModule_1(nn.Module):
    def __init__(self):
        super(MyModule_1, self).__init__()
        self.sigmoid = nn.Sigmoid()

    def forward(self, input):
        output = self.sigmoid(input)
        return output


model_1 = MyModule_1()
writer = SummaryWriter("logs11")
step = 0
for data in dataloader:
    imgs, targets = data
    for i, img in enumerate(imgs):
        input_img_hwc = img.permute(1, 2, 0)
        writer.add_image('input', input_img_hwc, step, dataformats="HWC")
    output = model_1(imgs)
    for i, img in enumerate(imgs):
        output_img_hwc = img.permute(1, 2, 0)
        writer.add_image('output', output_img_hwc, step, dataformats="HWC")
    step = step + 1
writer.close()