Catalog
About
copick album catalog
sharing copick tools
model-search
/
unet-model-search
/ 0.0.17
UNet with Optuna optimization
Optimization of UNet using Optuna with Copick data.
Tags
copick
plane
fitting
Solution written by
Kyle Harrington and Zhuowen Zhao
License of solution
MIT
Source Code
View on GitHub
Arguments
--copick_config_path
Path to the Copick configuration JSON file. (default value: PARAMETER_VALUE)
--voxel_spacing
Voxel spacing used to scale pick locations. (default value: PARAMETER_VALUE)
--tomo_type
Tomogram type to use for each tomogram. (default value: PARAMETER_VALUE)
--epochs
Number of training epochs. (default value: PARAMETER_VALUE)
--num_classes
Number of classes for segmentation, excluding the background class. (default value: PARAMETER_VALUE)
--num_trials
Number of trials for Optuna optimization. (default value: PARAMETER_VALUE)
--batch_size
Batch size for the DataLoader. (default value: PARAMETER_VALUE)
--random_seed
Random seed for reproducibility. (default value: 17171)
Usage instructions
Please follow
this link
for details on how to install and run this solution.