model_460225098_swin_t_base.py

Model Overview

A base-scale implementation of the swin t architecture, built for matching tasks.

Architecture

• Architecture: swin t
• Scale: base
• Attention: standard
• Fusion strategy: bilinear
• Task head: matching
• Activation: gelu tanh
• Normalization: groupnorm
• Initialization: xavier

Training

• Optimizer: sgd
• LR scheduler: polynomial

Files

• model_460225098_swin_t_base.py — main artifact of this repository

License

See the license field above.