pytorch自己给卷积层初始化

import numpy as np
import torchvision.models as models
import torch
w = torch.nn.Conv2d(2, 2, 3, padding=1)
print("w的权重：", w.weight)

q = torch.nn.Conv2d(2, 2, 3, padding=1)
print("q的权重：", q.weight)
w.weight = q.weight
print("更行后w的权重：", w.weight)
print(w.weight == q.weight)

论文中需要我对不同的卷积层进行不同的初始化