brianwilliams's picture
Upload 2 files
3e63855 verified
|
Raw History Blame Contribute Delete
755 Bytes
metadata
license: cc-by-4.0
tags:
  - adafactor
  - batchnorm
  - bilinear
  - contrastive
  - mish
  - mobilevit
  - onecycle
  - sliding-window
  - small
  - xavier-uniform

train.py

Model Overview

A small-scale implementation of the mobilevit architecture, built for contrastive tasks.

Architecture

  • Architecture: mobilevit
  • Scale: small
  • Attention: sliding window
  • Fusion strategy: bilinear
  • Task head: contrastive
  • Activation: mish
  • Normalization: batchnorm
  • Initialization: xavier uniform

Training

  • Optimizer: adafactor
  • LR scheduler: onecycle

Files

  • train.py — main artifact of this repository

License

See the license field above.