Unable to extract features using huggingface swin transformer model

1

I need to use swin transfomer as a backbone for my SVM model. I need to extract the features first, therefore I am trying to remove the last layer and train the model. This is a sample executable code.

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import numpy as np

HUB_URL = "SharanSMenon/swin-transformer-hub:main"
MODEL_NAME = "swin_tiny_patch4_window7_224"
model = torch.hub.load(HUB_URL, MODEL_NAME, pretrained=True)
model = nn.Sequential(*list(model.children())[:-1])          #--> If you comment this line, the code is executing
for param in model.parameters():
    param.requires_grad = False


dummy_tensor = torch.randn(32, 3, 224, width)

# Print the shape of the dummy tensor
model(dummy_tensor)

image
image655×622 122 KB

What am I missing, I tried the same process with resnet50 and it worked fine. Why am I not able to remove the last layer and get only the output features? what should I do? any suggestions?

2

I cannot download the model as I’m running into HTTPError: rate limit exceeded.
However, you could check which modules model.children() returns and check if one of them isn’t implementing the forward pass.

1 Like