New layer parameters initialization for pre-trained model

1

I want to modify the pre-trained model and train it.
For example, I use the resnet50 model in torchvision.
I cancel the last fc layer
Then I use a new transposed convolution layer and a new maxpool layer and a new classifier layer.

My question: are these three new layers’ parameters already initialized?
Or I need to initialize them with method like “Xavier” ?

I checked the values of these three layers, and they are not zero. I don’t know whether they are already initialized.
And why they are not equal to zero? Where do these values come from?

Thanks for your help!

2

Initializing new layers with new method will override any value present, if it exists.

4 
import torchvision.models as models
import torch.nn as nn

class Net(nn.Module):
    def __init__(self , model):
        super(Net, self).__init__()
        
        self.resnet_layer = nn.Sequential(*list(model.children())[:-2])
        
        self.transion_layer = nn.ConvTranspose2d(2048, 2048, kernel_size=14, stride=3)
        self.pool_layer = nn.MaxPool2d(32)  
        self.Linear_layer = nn.Linear(2048, 8)
        
    def forward(self, x):
        x = self.resnet_layer(x)
 
        x = self.transion_layer(x)
 
        x = self.pool_layer(x)
 
        x = x.view(x.size(0), -1) 
 
        x = self.Linear_layer(x)
        
        return x

res = models.resnet50(pretrained=True)

#model = Net(res)
#fc_features = res.fc.in_features

#res.fc = nn.Linear(fc_features, 10)

print(res.state_dict()['fc.weight'].shape)

I use this code and I don’t know which part do the initialization.
The three new layers are not exist in the pre-trained model.

Thanks!