model_568203494_deit_small.py

Model Overview

A small-scale implementation of the deit architecture, built for classification tasks.

Architecture

• Architecture: deit
• Scale: small
• Attention: sparse
• Fusion strategy: bilinear
• Task head: classification
• Activation: swish
• Normalization: instancenorm
• Initialization: kaiming normal

Training

• Optimizer: rmsprop
• LR scheduler: constant warmup

Files

• model_568203494_deit_small.py — main artifact of this repository

License

See the license field above.