Fiji gets stuck at Trainable Weka Segmentation

[Xiaoxiong Xing]

Dear users,

My Fiji sometimes gets stuck at "*Filtering feature stack by selected
attributes...*" when I try to apply a classifier to a new image or an image
stack. However, the same operation sometimes works fine, which makes me
fill weird.

Are there anyone have the same problem?

Sincerely,
Xiaoxiong

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html

[Ignacio Arganda-Carreras]

Dear Xiaoxiong,

Can you tell us more about the problem? What is the size of the image
you're using? Your system (Linux, Mac, Windows)? 32 or 64 bit? Your RAM?

Thanks!

ignacio


On Tue, Mar 25, 2014 at 8:18 PM, Xiaoxiong Xing <[hidden email]>wrote:

> Dear users,
>
> My Fiji sometimes gets stuck at "*Filtering feature stack by selected
> attributes...*" when I try to apply a classifier to a new image or an image
> stack. However, the same operation sometimes works fine, which makes me
> fill weird.
>
> Are there anyone have the same problem?
>
> Sincerely,
> Xiaoxiong
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

--
Ignacio Arganda-Carreras, Ph.D.
Seung's lab, 46-5065
Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology
43 Vassar St.
Cambridge, MA 02139
USA

Phone: [phone]
Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html

[Xiaoxiong Xing]

Dear Ignacio,

I am running Scientific Linux 6.0, 64 bit version. The data is composed of
738 slices of 738*738 8 bit images, in total about 400 MB, but I am using a
high performance machine which contains 16 CPUs and 128 GB memory, so it
shouldn't be the problem.

Today I found that Fiji Weka plugin got stuck if it tried to process a
black image and if I removed the black images, it then can move forward. I
am not sure if it's a bug of the plugin.

Thanks a lot.
Xiaoxiong


2014-03-26 3:41 GMT-06:00 Ignacio Arganda-Carreras <
[hidden email]>:

> Dear Xiaoxiong,
>
> Can you tell us more about the problem? What is the size of the image
> you're using? Your system (Linux, Mac, Windows)? 32 or 64 bit? Your RAM?
>
> Thanks!
>
> ignacio
>
>
> On Tue, Mar 25, 2014 at 8:18 PM, Xiaoxiong Xing <[hidden email]
> >wrote:
>
> > Dear users,
> >
> > My Fiji sometimes gets stuck at "*Filtering feature stack by selected
> > attributes...*" when I try to apply a classifier to a new image or an
> image
> > stack. However, the same operation sometimes works fine, which makes me
> > fill weird.
> >
> > Are there anyone have the same problem?
> >
> > Sincerely,
> > Xiaoxiong
> >
> > --
> > ImageJ mailing list: http://imagej.nih.gov/ij/list.html
> >
>
>
>
> --
> Ignacio Arganda-Carreras, Ph.D.
> Seung's lab, 46-5065
> Department of Brain and Cognitive Sciences
> Massachusetts Institute of Technology
> 43 Vassar St.
> Cambridge, MA 02139
> USA
>
> Phone: [phone]
> Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html

[Ignacio Arganda-Carreras]

Dear Xiaoxiong,


> I am running Scientific Linux 6.0, 64 bit version. The data is composed of
> 738 slices of 738*738 8 bit images, in total about 400 MB, but I am using a
> high performance machine which contains 16 CPUs and 128 GB memory, so it
> shouldn't be the problem.
>

I see. Do you train on an image of that size? Or you want to apply a
trained classifier on such an image?

You might be interested on Larry LIndsey's plugin to run the classifier in
a cluster: http://fiji.sc/Fiji_Archipelago


>
> Today I found that Fiji Weka plugin got stuck if it tried to process a
> black image and if I removed the black images, it then can move forward. I
> am not sure if it's a bug of the plugin.
>
>
Weird! Cand you send me a couple of the slices (some black ones too) to
reproduce the error in my machine?


> Thanks a lot.
>

Thank you for reporting!

ignacio

> Xiaoxiong
>
>
> 2014-03-26 3:41 GMT-06:00 Ignacio Arganda-Carreras <
> [hidden email]>:
>
> > Dear Xiaoxiong,
> >
> > Can you tell us more about the problem? What is the size of the image
> > you're using? Your system (Linux, Mac, Windows)? 32 or 64 bit? Your RAM?
> >
> > Thanks!
> >
> > ignacio
> >
> >
> > On Tue, Mar 25, 2014 at 8:18 PM, Xiaoxiong Xing <[hidden email]
> > >wrote:
> >
> > > Dear users,
> > >
> > > My Fiji sometimes gets stuck at "*Filtering feature stack by selected
> > > attributes...*" when I try to apply a classifier to a new image or an
> > image
> > > stack. However, the same operation sometimes works fine, which makes me
> > > fill weird.
> > >
> > > Are there anyone have the same problem?
> > >
> > > Sincerely,
> > > Xiaoxiong
> > >
> > > --
> > > ImageJ mailing list: http://imagej.nih.gov/ij/list.html
> > >
> >
> >
> >
> > --
> > Ignacio Arganda-Carreras, Ph.D.
> > Seung's lab, 46-5065
> > Department of Brain and Cognitive Sciences
> > Massachusetts Institute of Technology
> > 43 Vassar St.
> > Cambridge, MA 02139
> > USA
> >
> > Phone: [phone]
> > Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html
> >
> > --
> > ImageJ mailing list: http://imagej.nih.gov/ij/list.html
> >
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

--
Ignacio Arganda-Carreras, Ph.D.
Seung's lab, 46-5065
Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology
43 Vassar St.
Cambridge, MA 02139
USA

Phone: [phone]
Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html

[clarkj]

Hi, I'm having a similar issue, but I'm only analyzing one image with 5 classes. Granted it is a large 4400X4000 image from a 24MP DSLR. I get the following messages...

"Warning: at least one dimension of the image is larger than 1024 pixels.
Feature stack creation and classifier training might take some time depending on your computer.
Error when updating feature stack.
Feature stack was not updated.
The traning did not finish."

I'm running FIJI on a Macbook Pro 2.2 GHz i7 core and 8 GB of Ram.

Thanks

Jeff

[Robin]

Hi,

I have the same issue with the WEKA segmentation plugin.
I can train a classifier, the segmentation looks nice, but when I try to apply the classifier on another image Fiji gets stuck half way through at "Filtering stack by selected attributes".

I am using a Mac Book Pro; 3Ghz intel Core i7; OSX 10.9.3; 8GB RAM.

I would also need some advice on how to run this classifier in batch mode and keep the file names between source image and classified image consistent.

Many thanks for your input,

R

[Robin]

Hi,

I've reduced the size of my images by factor 4 and could easily complete the task.

Here is the workflow I used:

1. Maximum Intensity Projection (MIP) of Z-stack .stk files.
2. Auto level.
3. Resize MIPs.
4. Train classifier and save it as .model file.
5. Apply classifier; all files in complete directory.
6. Save output files into new directory and do not open in FIJI.

On my Mac Book Pro; 3Ghz intel Core i7; OSX 10.9.3; 8GB RAM,
the job took about 10 mins.

R

[Ignacio Arganda-Carreras]

Hello Robin,

I'm glad to hear you could solve the problem yourself. Please, let me know
if you need any further help.

Best,

ignacio


On Mon, Jun 30, 2014 at 9:43 AM, Robin <[hidden email]> wrote:

> Hi,
>
> I've reduced the size of my images by factor 4 and could easily complete
> the
> task.
>
> Here is the workflow I used:
>
> 1. Maximum Intensity Projection (MIP) of Z-stack .stk files.
> 2. Auto level.
> 3. Resize MIPs.
> 4. Train classifier and save it as .model file.
> 5. Apply classifier; all files in complete directory.
> 6. Save output files into new directory and do not open in FIJI.
>
> On my Mac Book Pro; 3Ghz intel Core i7; OSX 10.9.3; 8GB RAM,
> the job took about 10 mins.
>
> R
>
>
>
> --
> View this message in context:
> http://imagej.1557.x6.nabble.com/Fiji-gets-stuck-at-Trainable-Weka-Segmentation-tp5007076p5008489.html
> Sent from the ImageJ mailing list archive at Nabble.com.
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

--
Ignacio Arganda-Carreras, Ph.D.
Seung's lab, 46-5065
Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology
43 Vassar St.
Cambridge, MA 02139
USA

Phone: [phone]
Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html