Extra Dense Layer in the end of the network architecture

There is currently an extra layer at the end of the architecture. This does not figure on the `master `branch or here https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py

Compare the repository's network architecture with the referenced torchvision resnet.py implementation, starting from the model definition or entry point that constructs the final layers. Confirm where the extra dense layer is introduced and verify that the resulting architecture matches the intended design after the discrepancy is addressed.

Written by the indexing model from the issue text.