Commit 54b04934 authored by Wenqi Li's avatar Wenqi Li

Merge branch 'revising-config' into 'master'

Revising config

See merge request !4
parents e6db0c09 c9755fc0
[config]
version = 1.0
[download]
url = http://cmic.cs.ucl.ac.uk/platform/niftynetexamples/OASIS.tar.gz
[data]
url = http://cmic.cs.ucl.ac.uk/platform/niftynetexamples/OASIS.tar.gz?dl=1
action = expand
destination = data
Please see the [NiftyNet project page](https://cmiclab.cs.ucl.ac.uk/CMIC/NiftyNet).
Please see the [Model zoo entries](./model_zoo.md)
and [NiftyNet project page](https://cmiclab.cs.ucl.ac.uk/CMIC/NiftyNet).
NiftyNetExampleServer is part of an automatic download system. You don't need to clone this project.
\ No newline at end of file
[config]
version = 1.0
[download]
url = http://cmic.cs.ucl.ac.uk/platform/niftynetexamples/brain_parcellation.tar.gz
action = expand
destination = examples
[config]
version = 1.0
[download]
url = https://www.dropbox.com/s/yddopkblhe7gfsj/dense_vnet_abdominal_ct_model_zoo.tar.gz?dl=1
[code]
local_id = dense_vnet_abdominal_ct
url = https://www.dropbox.com/s/ptu46os7lfmj0dl/dense_vnet_abdominal_ct_code_config.tar.gz?dl=1
action = expand
destination = models
destination = extensions
[data]
local_id = dense_vnet_abdominal_ct
url = https://www.dropbox.com/s/5fk0m9v12if5da9/dense_vnet_abdominal_ct_model_zoo_data.tar.gz?dl=1
action = expand
destination = data
[weights]
local_id = dense_vnet_abdominal_ct
url = https://www.dropbox.com/s/zvc8stqo6womvou/dense_vnet_abdominal_ct_weights.tar.gz?dl=1
action = expand
destination = models
\ No newline at end of file
......@@ -14,19 +14,30 @@ nearby organs (liver, gallbladder, spleen, left kidney).
## Downloading model zoo files
If you cloned the NiftyNet repository, the network weights and examples data can be downloaded with the command
`python net_download.py dense_vnet_abdominal_ct_model_zoo dense_vnet_abdominal_ct_model_zoo_data`.
```bash
python net_download.py dense_vnet_abdominal_ct_model_zoo
```
If you install NiftyNet via pip, you won't have the net_download feature yet. You can download the
Alternatively, you can download the
[model zoo entry](https://www.dropbox.com/s/yddopkblhe7gfsj/dense_vnet_abdominal_ct_model_zoo.tar.gz?dl=1)
and the [example data](https://www.dropbox.com/s/5fk0m9v12if5da9/dense_vnet_abdominal_ct_model_zoo_data.tar.gz?dl=1) manually.
Unzip dense_vnet_abdominal_ct_model_zoo.tar.gz into ~/niftynet/models/dense_vnet_abdominal_ct_model_zoo/ and dense_vnet_abdominal_ct_model_zoo_data.tar.gz into
~/niftynet/data/dense_vnet_abdominal_ct_model_zoo_data/.
Unzip `dense_vnet_abdominal_ct_model_zoo.tar.gz` into
`~/niftynet/models/dense_vnet_abdominal_ct_model_zoo/` and
`dense_vnet_abdominal_ct_model_zoo_data.tar.gz` into
`~/niftynet/data/dense_vnet_abdominal_ct_model_zoo_data/`.
Make sure that the model directory (`~/niftynet/models/` by default) is on the PYTHONPATH.
Make sure that the model directory (`~/niftynet/models/` by default) is on the `PYTHONPATH`.
## Generating segmentations for example data
Generate segmentations for the included example image with the command `net_segment inference -c ~/niftynet/models/dense_vnet_abdominal_ct_model_zoo/config.ini`. Replace `net_segment` with `python net_segment.py` if you cloned the NiftyNet repository. Replace `~/niftynet/` if you specified a custom download path in the `net_download` command.
Generate segmentations for the included example image with the command
```bash
net_segment inference -c ~/niftynet/extensions/dense_vnet_abdominal_ct/config.ini
```
Replace `net_segment` with `python net_segment.py` if you cloned the NiftyNet repository.
Replace `~/niftynet/` if you specified a custom download path in the `net_download` command.
## Generating segmentations for your own data
......@@ -38,7 +49,7 @@ field-of-view set to -1000.
### Editing the configuration file
Make a copy of the configuration file `~/niftynet/models/dense_vnet_abdominal_ct_model_zoo/config.ini` to a location of your choice.
Make a copy of the configuration file `~/niftynet/extensions/dense_vnet_abdominal_ct/config.ini` to a location of your choice.
You may need to change the `path_to_search` and `filename_contains` lines in the configuration file to point to the correct paths for your images. You can also change the `save_seg_dir` setting to change where the segmentations are saved.
### Generating segmentations
......
[config]
version = 1.0
[code]
local_id = dense_vnet_abdominal_ct
url = https://www.dropbox.com/s/ptu46os7lfmj0dl/dense_vnet_abdominal_ct_code_config.tar.gz?dl=1
action = expand
destination = extensions
\ No newline at end of file
[config]
version = 1.0
[download]
[data]
local_id = dense_vnet_abdominal_ct
url = https://www.dropbox.com/s/5fk0m9v12if5da9/dense_vnet_abdominal_ct_model_zoo_data.tar.gz?dl=1
action = expand
destination = data
[config]
version = 1.0
[weights]
local_id = dense_vnet_abdominal_ct
url = https://www.dropbox.com/s/zvc8stqo6womvou/dense_vnet_abdominal_ct_weights.tar.gz?dl=1
action = expand
destination = models
\ No newline at end of file
[config]
version = 1.0
[download]
url = http://cmic.cs.ucl.ac.uk/platform/niftynetexamples/highres3dnet.tar.gz
action = expand
destination = examples
[config]
version = 1.0
[data]
local_id = OASIS
url = http://cmic.cs.ucl.ac.uk/platform/niftynetexamples/OASIS.tar.gz?dl=1
action = expand
destination = data
[weights]
local_id = highres3dnet_brain_parcellation
url = https://www.dropbox.com/s/nxg2ixs9rh1p9ri/highres3dnet_brain_parcellation_weights.tar.gz?dl=1
action = expand
destination = models
[network_inference_config]
local_id = highres3dnet_brain_parcellation
url = https://www.dropbox.com/s/r2q08q1kkd534p4/highres3dnet_brain_parcellation_config.tar.gz?dl=1
action = expand
destination = extensions
\ No newline at end of file
# Automatic brain parcellation on T1 MR with a high-resolution 3D net
This page describes how to acquire and use the network described in:
Li W., Wang G., Fidon L., Ourselin S., Cardoso M.J., Vercauteren T. (2017)
On the Compactness, Efficiency, and Representation of 3D
Convolutional Networks: Brain Parcellation as a Pretext Task.
In: Information Processing in Medical Imaging. IPMI 2017
This network parcellates 160 types of structures
(including 155 neuroanatomical structures) from brain MR images.
## Downloading model zoo files
If you cloned the NiftyNet repository,
the network weights and examples data can be downloaded with the command
```bash
python net_download.py highres3dnet_brain_parcellation_model_zoo
```
## Generating segmentations for example data
Generate segmentations for the included example image with the command
```bash
net_segment inference -c ~/niftynet/extensions/highres3dnet_brain_parcellation/highres3dnet_config_eval.ini
```
Replace `net_segment` with `python net_segment.py` if you cloned the NiftyNet repository.
Replace `~/niftynet/` if you specified a custom download path in the `net_download` command.
\ No newline at end of file
[config]
version = 1.0
[network_inference_config]
local_id = highres3dnet_brain_parcellation
url = https://www.dropbox.com/s/r2q08q1kkd534p4/highres3dnet_brain_parcellation_config.tar.gz?dl=1
action = expand
destination = extensions
\ No newline at end of file
[config]
version = 1.0
[weights]
local_id = highres3dnet_brain_parcellation
url = https://www.dropbox.com/s/nxg2ixs9rh1p9ri/highres3dnet_brain_parcellation_weights.tar.gz?dl=1
action = expand
destination = models
\ No newline at end of file
......@@ -4,6 +4,6 @@ This page lists NiftyNet networks pre-trained for specific tasks. Information ab
| Name | Description |
| --- | --- |
| [dense_vnet_abdominal_ct_model_zoo](https://cmiclab.cs.ucl.ac.uk/CMIC/NiftyNetExampleServer/blob/master/dense_vnet_abdominal_ct_model_zoo.md) | Segment multiple organs from abdominal CT |
| [ultrasound_simulator_gan_model_zoo](https://cmiclab.cs.ucl.ac.uk/CMIC/NiftyNetExampleServer/blob/master/ultrasound_simulator_gan_model_zoo.md) | Generate simulated ultrasound images at specified poses |
| [dense_vnet_abdominal_ct_model_zoo](./dense_vnet_abdominal_ct_model_zoo.md) | Segment multiple organs from abdominal CT |
| [ultrasound_simulator_gan_model_zoo](./ultrasound_simulator_gan_model_zoo.md) | Generate simulated ultrasound images at specified poses |
| [highres3dnet_brain_parcellation_model_zoo](./highres3dnet_brain_parcellation_model_zoo.md) | Brain parcellation from T1 MR images |
[config]
version = 1.0
[download]
url = https://www.dropbox.com/s/hny7xbkisjrryys/ultrasound_simulator_gan_model_zoo.tar.gz?dl=1
[data]
local_id = ultrasound_simulator_gan
url = https://www.dropbox.com/s/hu1i8yjdptwq6wj/ultrasound_simulator_gan_model_zoo_data.tar.gz?dl=1
action = expand
destination = data
[weights]
local_id = ultrasound_simulator_gan
url = https://www.dropbox.com/s/95smm4i464nwczm/ultrasound_simulator_gan_weights.tar.gz?dl=1
action = expand
destination = models
[code]
local_id = ultrasound_simulator_gan
url = https://www.dropbox.com/s/089l4ixd2k7fiyy/ultrasound_simulator_gan_code.tar.gz?dl=1
action = expand
destination = extensions
\ No newline at end of file
......@@ -8,7 +8,9 @@ Yipeng Hu, Eli Gibson, Li-Lin Lee, Weidi Xie, Dean C. Barratt, Tom Vercauteren,
## Downloading model zoo file and conditioning data
If you cloned the NiftyNet repository, the network weights and examples data can be downloaded with the command
`python net_download.py ultrasound_simulator_gan_model_zoo ultrasound_simulator_gan_model_zoo_data`.
```bash
python net_download.py ultrasound_simulator_gan_model_zoo
```
If you install NiftyNet via pip, you won't have the net_download feature yet. You can download the
[model zoo entry](https://www.dropbox.com/s/yddopkblhe7gfsj/dense_vnet_abdominal_ct_model_zoo.tar.gz?dl=1)
......@@ -22,13 +24,20 @@ This network generates ultrasound images conditioned by a coordinate map. Some e
## Generating segmentations for example data
Generate segmentations for the included example conditioning data with the command `net_gan inference -c ~/niftynet/models/ultrasound_simulator_gan_model_zoo/config.ini`. Replace `net_segment` with `python net_gan.py` if you cloned the NiftyNet repository. Replace `~/niftynet/` if you specified a custom download path in the `net_download` command.
Generate segmentations for the included example conditioning data with the command
```bash
net_gan inference -c ~/niftynet/extensions/ultrasound_simulator_gan/config.ini
```
Replace `net_segment` with `python net_gan.py` if you cloned the NiftyNet repository.
Replace `~/niftynet/` if you specified a custom download path in the `net_download` command.
## Generating segmentations for additional conditioning data
## Editing the configuration file
Make a copy of the configuration file `~/niftynet/models/ultrasound_simulator_gan_model_zoo/config.ini` to a location of your choice.
Make a copy of the configuration file `~/niftynet/extensions/ultrasound_simulator_gan/config.ini` to a location of your choice.
You may need to change the `path_to_search` and `filename_contains` lines in the configuration file to point to the correct paths for your conditioning data. You can also change the `save_seg_dir` setting to change where the segmentations are saved.
## Generating samples
......
[config]
version = 1.0
[code]
local_id = ultrasound_simulator_gan
url = https://www.dropbox.com/s/089l4ixd2k7fiyy/ultrasound_simulator_gan_code.tar.gz?dl=1
action = expand
destination = extensions
\ No newline at end of file
[config]
version = 1.0
[download]
[data]
local_id = ultrasound_simulator_gan
url = https://www.dropbox.com/s/hu1i8yjdptwq6wj/ultrasound_simulator_gan_model_zoo_data.tar.gz?dl=1
action = expand
destination = data
[config]
version = 1.0
[weights]
local_id = ultrasound_simulator_gan
url = https://www.dropbox.com/s/95smm4i464nwczm/ultrasound_simulator_gan_weights.tar.gz?dl=1
action = expand
destination = models
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment