not seeing plot when i execute model.plot()

[Mawul4j]

I would like to reproduce the results in figure 4 of the paper "Nested Variational Compression in Deep Gaussian Processes" from "Nested Deep GPs.ipynb" notebook but model.plot() does not show any figure. Please what am i doing wrong?

[lawrennd]

@mzwiessele is this associated with the changes of the plotting code for
GPy?

On Mon, Feb 29, 2016 at 9:48 PM, Mawul4j notifications@github.com wrote:

I would like to reproduce the results in "Nested Deep GPs" notebook but
model.plot() does not show any figure. Please what am i doing wrong?

—
Reply to this email directly or view it on GitHub
#5.

[mzwiessele]

Could you provide a code snippet reproducing the error and your python version, so we can narrow it down? Also which GPy are you using?

On 01 Mar 2016, at 06:36, Neil Lawrence notifications@github.com wrote:

@mzwiessele is this associated with the changes of the plotting code for
GPy?

On Mon, Feb 29, 2016 at 9:48 PM, Mawul4j notifications@github.com wrote:

I would like to reproduce the results in "Nested Deep GPs" notebook but
model.plot() does not show any figure. Please what am i doing wrong?

—
Reply to this email directly or view it on GitHub
#5.

—
Reply to this email directly or view it on GitHub.

[Mawul4j]

Please, is there anything i am doing wrong?

[Mawul4j]

I have managed to upgrade GPy to version 0.9.4 but this issue persists.
Follow up: Is there any solution to this?

[mzwiessele]

I don't think it has anything to do with you doing something wrong. I cannot be sure though. Could you give us a minimalist example of when it goes wrong? So we can run it on newer versions of GPy and see how it performs there? Also we might be able to find the problem, if there is one in DeepGP.

Thanks

On 02 Mar 2016, at 10:48, Mawul4j notifications@github.com wrote:

I have managed to upgrade GPy to version 0.9.4 but this issue persists.
Follow up: Is there any solution to this?

—
Reply to this email directly or view it on GitHub.

[Mawul4j]

Okay.
when i execute "model.plot()", basically it shows nothing
Also when i execute
for layer in model.layers:
----> layer.plot()
ValueError: x and y must have same first dimension

I don't know if that makes sense.

[mzwiessele]

Do you have a piece of code, which we can run, which reproduces the error? That would be very helpful in order to see where the problem lies.

Thanks

On 02 Mar 2016, at 14:03, Mawul4j notifications@github.com wrote:

Okay.
when i execute "model.plot()", basically it shows nothing
Also when i execute
for layer in model.layers:
----> layer.plot()
ValueError: x and y must have same first dimension

I don't know if that makes sense.

—
Reply to this email directly or view it on GitHub.

[Mawul4j]

Nested.zip

[thangbui]

Have you tried commenting out this? https://github.com/SheffieldML/deepGPy/blob/master/step_fn_demo.py#L4

[Mawul4j]

Yes but it did not solve the problem for me. Did it work for you?

[thangbui]

OK nevermind my previous comment as you were trying to run the notebook, not the step function demo script.

I couldn't replicate the problem you have on a mac with the latest GPy.

[Mawul4j]

The plotting.py file contains code that only covers cases where input and output dimensions are ==1.
Could it be that the complete plotting.py file has not been uploaded here on github?

[jameshensman]

Could it be that the complete plotting.py file has not been uploaded here
on github?

No, if it works for Thang, it's on github.

If your output dimension is larger than 1, I suspect that simply no plot
will appear.

James.

On 5 April 2016 at 22:44, Mawul4j notifications@github.com wrote:

The plotting.py file contains code that only covers cases where input and
output dimensions are ==1.
Could it be that the complete plotting.py file has not been uploaded here
on github?

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub
#5 (comment)

[Mawul4j]

@jameshensman Basically, i want to reproduce figure 4 of the paper "Nested Variational Compression in Deep Gaussian Processes". So, I ran the example in the notebook on robot wireless data to get that result.
Maybe i am doing this wrong, but can you please show me how figure 4 of that paper was produced with DeepGPy?
I believe Thang was helping with the step function demo.