Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
N
NiftyNetExampleServer
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Operations
Operations
Incidents
Environments
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
CMIC
NiftyNetExampleServer
Commits
2f1bdc4e
Commit
2f1bdc4e
authored
Feb 03, 2018
by
Wenqi Li
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Update mr_ct_regression_model_zoo.md
parent
dec04cb5
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
9 additions
and
9 deletions
+9
-9
mr_ct_regression_model_zoo.md
mr_ct_regression_model_zoo.md
+9
-9
No files found.
mr_ct_regression_model_zoo.md
View file @
2f1bdc4e
...
...
@@ -19,12 +19,12 @@ net_download mr_ct_regression_model_zoo
## Initial training
Command line parameters:
``--starting_iter 0 --max_iter 100``
Command line parameters:
``--starting_iter 0 --max_iter 100
0
``
```
bash
python net_run.py train
\
-a
niftynet.contrib.regression_weighted_sampler.isample_regression.ISampleRegression
\
-c
~/niftynet/extensions/mr_ct_regression/net_isampler.ini
\
--starting_iter
0
--max_iter
100
--starting_iter
0
--max_iter
100
0
```
## Generating error maps
...
...
@@ -37,17 +37,17 @@ the errors (elementwise squared differences) will be generated to
python net_run.py inference
\
-a
niftynet.contrib.regression_weighted_sampler.isample_regression.ISampleRegression
\
-c
~/niftynet/extensions/mr_ct_regression/net_isampler.ini
\
--inference_iter
100
--spatial_window_size
240,240,1
--batch_size
4
--error_map
True
--inference_iter
100
0
--spatial_window_size
240,240,1
--batch_size
4
--error_map
True
```
## Continue training by sampling according to the error maps:
Command line parameters
``--starting_iter -1``
indicate training the model from the most recently saved checkpoint (at iteration 100).
indicate training the model from the most recently saved checkpoint (at iteration 100
0
).
```
bash
python net_run.py train
\
-a
niftynet.contrib.regression_weighted_sampler.isample_regression.ISampleRegression
\
-c
~/niftynet/extensions/mr_ct_regression/net_isampler.ini
\
--starting_iter
-1
--max_iter
2
00
--starting_iter
-1
--max_iter
15
00
```
## Combine them together
...
...
@@ -58,8 +58,8 @@ python net_download.py mr_ct_regression_model_zoo
python net_run.py train
\
-a
niftynet.contrib.regression_weighted_sampler.isample_regression.ISampleRegression
\
-c
~/niftynet/extensions/mr_ct_regression/net_isampler.ini
\
--starting_iter
0
--max_iter
100
for
max_iter
in
`
seq
200 100 5
000
`
--starting_iter
0
--max_iter
100
0
for
max_iter
in
`
seq
1500 500 10
000
`
do
python net_run.py inference
\
-a
niftynet.contrib.regression_weighted_sampler.isample_regression.ISampleRegression
\
...
...
@@ -72,8 +72,8 @@ do
--starting_iter
-1
--max_iter
$max_iter
done
```
This script runs training for
5
000 iterations,
and new sampling weights are generated at every
1
00 iterations.
This script runs training for
10
000 iterations,
and new sampling weights are generated at every
5
00 iterations.
To see the training/validation curves using tensorboard:
```
bash
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment