/edge-popup

:lollipop: Unofficial reproduction of the paper "What's Hidden in a Randomly Weighted Neural Network?"

Primary LanguageJupyter NotebookMIT LicenseMIT

edge-popup

Unofficial reproduction of the paper What's Hidden in a Randomly Weighted Neural Network?.

A Subnetwork

Status: in development.

Results

Dataset Arch Epochs edge-popup Commit Accuracy # Runs
Imagenette xresnet50 5 yes 55e34a6b 76.18% 5, mean
Imagenette xresnet50 5 no 55e34a6b 80.94% 5, mean
Imagenette xresnet50 20 yes 55e34a6b 86.44% 5, mean
Imagenette xresnet50 20 no 55e34a6b 89.53% 5, mean
Paper (CIFAR-10, Conv 8) Reproduction (Imagewoof, xresnet50, 2f1f0b0d)
paper repro

ToDo

  • init
    • signed kaiming constant
    • kaiming normal
  • layers
    • Linear
    • Conv2d
    • BatchNorm2d
    • LSTM
  • tests
    • initializations / variance

Resources

Contributing

Any contributions are welcome.

Feel free to file an issue or send a pull request.