Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
OrcaSong
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Machine Learning
OrcaSong
Commits
666afcf1
Commit
666afcf1
authored
4 years ago
by
Daniel Guderian
Browse files
Options
Downloads
Patches
Plain Diff
Delete example_make_data_split_config.toml
parent
0cd9ef3f
No related branches found
Branches containing commit
No related tags found
Tags containing commit
1 merge request
!14
revive make_data_split
Changes
1
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
orcasong/tools/example_make_data_split_config.toml
+0
-69
0 additions, 69 deletions
orcasong/tools/example_make_data_split_config.toml
with
0 additions
and
69 deletions
orcasong/tools/example_make_data_split_config.toml
deleted
100644 → 0
+
0
−
69
View file @
0cd9ef3f
# Example configuration file for make_data_split.py
# --- Documentation for every config parameter that is available --- #
#
# Main Parameters
# ----------
# n_files_train : int
# Into how many files the training dataset should be split.
# If you don't want to have this dataset, comment out the line or delete it!
# n_files_validate : int
# Into how many files the validation dataset should be split.
# If you don't want to have this dataset, comment out the line or delete it!
# n_files_rest : int
# Into how many files the "rest" dataset should be split.
# If you don't want to have this dataset, comment out the line or delete it!
# output_file_folder : str
# Path to the folder, where all the output .list files (and the bash job scripts) should be stored.
# output_file_name : str
# String, that specifies the prefix of the filename of the output .list files.
# E.g. if = "xyzc_tight_0":
# xyzc_tight_0_train_0.list, xyzc_tight_0_validate_0.list, ...
# print_only : bool
# If only informationa about the input_groups should be printed, and no .list files should be made.
#
#
# Input Group Parameters
# ----------------------
# dir : str
# Path of the directory, where the files for this input group are located.
# run_ids_train/run_ids_validate/run_ids_rest : array
# Array, which specifies the range of the run_ids, that should be used for the training/validation.rest
# dataset of this input group.
# E.g. if [1,5], the script will put files from this input group with run_ids from 1 to 5 (including 1 and 5)
# to the training/validation/rest dataset.
# If you don't want to use a specific dataset for this input group, comment out the line or delete it!
#
# --- Documentation for every config parameter that is available --- #
# --- Main options ---#
n_files_train
=
3
n_files_validate
=
1
n_files_rest
=
0
output_file_folder
=
"/sps/km3net/users/guderian/NN_stuff/split_data_output/ORCA4/graph/ts/"
output_file_name
=
"test_list"
print_only
=
false
# only print information of your input_groups, don't make any .list files
# --- Main options ---#
# --- Input groups : these are the datafiles, that should be concatenated somehow --- #
[elec_cc]
dir
=
"/sps/km3net/users/guderian/NN_stuff/graphs/ORCA4/base/gsg_elecCC-CC_1-500GeV.km3sim/test/"
run_ids_train
=
[
6763
,
6767
]
run_ids_validate
=
[
6768
,
6769
]
[muon_nc]
dir
=
"/sps/km3net/users/guderian/NN_stuff/graphs/ORCA4/base/gsg_muonNC-NC_1-500GeV.km3sim/test/"
run_ids_train
=
[
6763
,
6767
]
run_ids_validate
=
[
6768
,
6769
]
# --- Input groups : these are the datafiles, that should be concatenated somehow --- #
\ No newline at end of file
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment