hw1-classify / README.md
marchenkoiryna's picture
Upload 2 files
5718094 verified
|
Raw
History Blame Contribute Delete
735 Bytes
metadata
license: apache-2.0
tags:
  - batchnorm
  - cosine
  - gated-fusion
  - lion
  - mobilevit
  - relu
  - retrieval
  - sliding-window
  - xavier
  - xlarge

predict.py

Model Overview

A xlarge-scale implementation of the mobilevit architecture, built for retrieval tasks.

Architecture

  • Architecture: mobilevit
  • Scale: xlarge
  • Attention: sliding window
  • Fusion strategy: gated fusion
  • Task head: retrieval
  • Activation: relu
  • Normalization: batchnorm
  • Initialization: xavier

Training

  • Optimizer: lion
  • LR scheduler: cosine

Files

  • predict.py — main artifact of this repository

License

See the license field above.