- returns segmentations and metrics. The first method returns the segmentations and metrics, the second method only computes segmentations and doesn't compute the metrics.
(segs, rand) = pygt.zwatershed_and_metrics(segTrue, aff_graph, eval_thresh_list, seg_save_thresh_list)segs: list of segmentationslen(segs) == len(seg_save_thresh_list)
rand: dictrand['V_Rand']: V_Rand score (scalar)rand['V_Rand_split']: list of score valueslen(rand['V_Rand_split']) == len(eval_thresh_list)
rand['V_Rand_merge']: list of score values,len(rand['V_Rand_merge']) == len(eval_thresh_list)
segs = pygt.zwatershed(aff_graph, eval_thresh_list)segs: list of segmentationslen(segs) == len(seg_save_thresh_list)
rand: dictrand['V_Rand']: V_Rand score (scalar)rand['V_Rand_split']: list of score valueslen(rand['V_Rand_split']) == len(eval_thresh_list)
rand['V_Rand_merge']: list of score values,len(rand['V_Rand_merge']) == len(eval_thresh_list)
- These next versions of the above methods save the segmentations to hdf5 files instead of returning them
3.
rand = pygt.zwatershed_and_metrics_h5(segTrue, aff_graph, eval_thresh_list, seg_save_thresh_list, seg_save_path)4.pygt.zwatershed_h5(aff_graph, eval_thresh_list, seg_save_path)
forked from csinva/conv-net-scripts
grisaitis/conv_net_scripts
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Scripts for evaluation of convolutional networks
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Jupyter Notebook 48.4%
- C++ 37.4%
- Makefile 13.5%
- Other 0.7%