learning rate, momentum和initial weight 对深度学习模型XOR的影响

import torch
import torch.utils.data
import torch.nn.functional as F
import numpy as np
import sys
class MyModel(torch.nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        # define structure of the network here
        self.in_hid  = torch.nn.Linear(2,2)
        self.hid_out = torch.nn.Linear(2,1)
    def forward(self, input):
        # apply network and return output
        hid_sum = self.in_hid(input)
        hidden  = torch.tanh(hid_sum)
        out_sum = self.hid_out(hidden)
        output  = torch.sigmoid(out_sum)
        return(output)

device = 'cpu'
input  = torch.Tensor([[0,0],[0,1],[1,0],[1,1]])
target = torch.Tensor([[0],[1],[1],[0]])

xor_dataset  =