pytorch 初始化

初始化

import matplotlib.pyplot as plt
import torch
import torch.nn as nn
from torch.utils.data import Dataset,DataLoader
import torch.optim as optim
import numpy as np
random_seed=1000
# np.random.seed(random_seed)
torch.manual_seed(random_seed)#自定义损失函数
class my_loss(nn.Module):def __init__(self):super().__init__()def forward(self, x, y):# loss = nn.L1Loss()(x,y)# loss=nn.MSELoss()(x,y)# total_sum=torch.sum(torch.pow(x,2)+torch.pow(y,2))# total_sum = torch.sum(torch.pow(x, 2))# loss=torch.div(loss,total_sum)# loss=torch.mean(torch.sub(y,x))loss=torch.mean(torch.pow(torch.abs(torch.sub(y,x)),1))return loss
# 定义模型
class TheModelClass(nn.Module):def __init__(self):hidden=15super(TheModelClass, self).__init__()self.fc1 = nn.Linear(1,hidden)# self.relu=nn.Sigmoid()

pytorch 初始化

初始化

import matplotlib.pyplot as plt
import torch
import torch.nn as nn
from torch.utils.data import Dataset,DataLoader
import torch.optim as optim
import numpy as np
random_seed=1000
# np.random.seed(random_seed)
torch.manual_seed(random_seed)#自定义损失函数
class my_loss(nn.Module):def __init__(self):super().__init__()def forward(self, x, y):# loss = nn.L1Loss()(x,y)# loss=nn.MSELoss()(x,y)# total_sum=torch.sum(torch.pow(x,2)+torch.pow(y,2))# total_sum = torch.sum(torch.pow(x, 2))# loss=torch.div(loss,total_sum)# loss=torch.mean(torch.sub(y,x))loss=torch.mean(torch.pow(torch.abs(torch.sub(y,x)),1))return loss
# 定义模型
class TheModelClass(nn.Module):def __init__(self):hidden=15super(TheModelClass, self).__init__()self.fc1 = nn.Linear(1,hidden)# self.relu=nn.Sigmoid()