A meta search space for encoder decoder networks.
Project description
A modular, user-centric tool to define fixed architectures analoguos to search spaces for semantic segmentation. The search strategy applied is random sampling, non-architectural hyperparameters are also covered. Builds on PyTorch (model instantiation, training) and Ray Tune (search, checkpointing).
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
encdecmeta-0.0.3.tar.gz
(21.3 kB
view hashes)
Built Distribution
encdecmeta-0.0.3-py3-none-any.whl
(28.6 kB
view hashes)
Close
Hashes for encdecmeta-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 593ccd9c0c95e123bb050921379508cb9b238daf7f5ec9be6bb6b01669b6f7b9 |
|
MD5 | 369cd7743f6c0706bacfeb10412f2114 |
|
BLAKE2b-256 | 525c20bd3a275adaae734c04e96dc11d85b4ada0781ea596090c9f5068f4a0d8 |