https://github.com/bencardoen/deep_loco
sample implementation of deeploco
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: biorxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.8%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
Repository
sample implementation of deeploco
Basic Info
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Fork of nboyd/deep_loco
Created over 7 years ago
· Last pushed over 7 years ago
https://github.com/bencardoen/deep_loco/blob/master/
## A fork of https://github.com/nboyd/deep_loco, all rights reserved to the orignal authors. # deep_loco A sample implementation of [deeploco](https://www.biorxiv.org/content/early/2018/02/16/267096). train_script.py trains a neural net to do localization using simulated data generated from a z-stack from the 2016 SMLM challenge. You'll need a machine with a (reasonably) powerful GPU to train quickly (set use_cuda=True). To try this on a new dataset you'll need a z-stack (see empirical_sim.py) and to make sure that the simulated data looks as similar as possible to the real data. This could be quite difficult: you'll need to adjust many hardcoded values in empirical_sim.py, as well as the generative model settings (in train_script.py). You might also need to modify the learning rate schedule of the network. localize.py gives an example of how to use a pretrained network to do localization.
Owner
- Name: Ben Cardoen
- Login: bencardoen
- Kind: user
- Location: Vancouver
- Company: https://github.com/sfu-mial
- Twitter: BenCardoen
- Repositories: 29
- Profile: https://github.com/bencardoen
PhD Student Computing Science @sfu-mial Simon Fraser University