Useful PyTorch Layers
Project description
Deep-Learning-Blocks
A library with customized PyTorch layers and model components.
What's available for use:
Layers:
- Funnel ReLU
- Flip-Invariant Conv2d
- Squeeze-Excitation Block
- Custom Multi-Head Self-Attention
Loss Functions:
- Focal Loss
- AUC Loss
- KL divergence Loss
Regularizer:
Self-supervised Learning:
Optimizers:
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
deepblocks-0.1.4.tar.gz
(19.4 kB
view hashes)
Built Distribution
deepblocks-0.1.4-py3-none-any.whl
(25.7 kB
view hashes)
Close
Hashes for deepblocks-0.1.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 60f20284988fbe6db40f96b1256c10304a9283089f12c31e73a968b4cdcef7d7 |
|
MD5 | 45a01d6e2359e8516e19766aa2f07d7e |
|
BLAKE2b-256 | 5fbd5ccfa904e795dbdffd39270540cf5346b425662df88d94dca0501ecfdb8a |