Adding gridsearch with parser to pysap #46
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 14 commits
April 3, 2018 13:32
…e to put reconstruct ??
… data is copied on disk, must be moved to ftp)
…dopt import ... Still not ready for PR
…ch example. Near ready to PR
finishing implementing gridsearch module
…of breaking line around binary operator
Pull Request Test Coverage Report for Build 130
💛 - Coveralls |
…f Sparse2D transforms. For now, there is still a bug unfound
update master on fork
merge master origin with upstream
|
Missing |
sfarrens
requested changes
Jun 29, 2018
pysap/plugins/mri/gridsearch/data.py
Outdated
| acc_factor=None): | ||
|
|
||
| ref = get_sample_data("mri-slice-nifti") | ||
| ref = _l2_normalize(ref.data) |
There was a problem hiding this comment.
I think this should probably be
ref.data = _l2_normalize(ref.data)| info['mask_type'] = mask_type | ||
| info['acc_factor'] = acc_factor | ||
|
|
||
| return ref.astype("complex128"),\ |
There was a problem hiding this comment.
This one also
return ref.data.astype("complex128"),\
sfarrens
requested changes
Jun 29, 2018
pysap/plugins/mri/gridsearch/data.py
Outdated
| # Sys import | ||
| import os.path as osp | ||
|
|
||
| import sys |
pysap/plugins/mri/gridsearch/data.py
Outdated
|
|
||
| # Specific import | ||
| from pysap.plugins.mri.reconstruct.utils import convert_mask_to_locations | ||
| from pysap.plugins.mri.reconstruct.utils import convert_locations_to_mask |
pysap/plugins/mri/gridsearch/data.py
Outdated
|
|
||
| _dirname_ = osp.dirname(osp.abspath(__file__)) | ||
| _data_dirname_ = osp.join(_dirname_, "data") | ||
| DATADIR = osp.join(osp.expanduser("~"), ".local", "share", "pysap") |
There was a problem hiding this comment.
Any reason why you do not simply use the following?
_data_dirname_ = osp.join(osp.expanduser("~"), ".local", "share", "pysap")| import logging | ||
|
|
||
| import argparse | ||
| import itertools |
| import itertools | ||
|
|
||
| # Third party import | ||
| import requests |
| # Third party import | ||
| import requests | ||
| import numpy as np | ||
| import matplotlib.pylab as plt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
WARNING: This code must be reviewed after PR #22 of Modopt package have been accepted. Also, it needs some data in .local/share/pysap, which can't be download for now from ftp.
Modifications
Thoses changes allows to use a gridsearch wrapper (in base/gridsearch) to multi-thread reconstructions on several parameters (passed as arrays) and also compute multiple metrics at once.
A working example is set in examples/ dir, it is really the main scripts of study_launcher.py and post_processing.py concatenated in one file. Read README in gridsearch plugin to see how it works.
Quickly, the principle is that study_launcher.py parses the config.ini file, with lists of parameters and metrics to try on the gridsearch. Then, the gridsearch is called on one of the reconstruction function. Results are stored in results/ folder and the post_processing.py script reads it, and compute statistics over it.