lewismichael's picture
Upload 2 files
baabfa1 verified
|
Raw
History Blame Contribute Delete
779 Bytes
metadata
license: bsd-3-clause
tags:
  - base
  - bilinear
  - classification
  - exponential
  - flash
  - gelu
  - groupnorm
  - poolformer
  - sgd
  - xavier

model_424787849_poolformer_base.py

Model Overview

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

Architecture

  • Architecture: poolformer
  • Scale: base
  • Attention: flash
  • Fusion strategy: bilinear
  • Task head: classification
  • Activation: gelu
  • Normalization: groupnorm
  • Initialization: xavier

Training

  • Optimizer: sgd
  • LR scheduler: exponential

Files

  • model_424787849_poolformer_base.py — main artifact of this repository

License

See the license field above.