emilywrvx's picture
Upload 2 files
950f30d verified
|
Raw
History Blame Contribute Delete
773 Bytes
metadata
license: cc-by-4.0
tags:
  - base
  - classification
  - instancenorm
  - onecycle
  - sgd
  - sliding-window
  - swish
  - tucker
  - vit
  - xavier-uniform

model_016552948_vit_base.py

Model Overview

A base-scale implementation of the vit architecture, built for classification tasks.

Architecture

  • Architecture: vit
  • Scale: base
  • Attention: sliding window
  • Fusion strategy: tucker
  • Task head: classification
  • Activation: swish
  • Normalization: instancenorm
  • Initialization: xavier uniform

Training

  • Optimizer: sgd
  • LR scheduler: onecycle

Files

  • model_016552948_vit_base.py — main artifact of this repository

License

See the license field above.