I'll try it.
many thanks
On Thursday, October 13, 2016 at 9:33:17 PM UTC+2, nouiz wrote:
>
> do you want 2d or 3d pooling? We merged (today I think) a good interface
> for pool 3d: theano.tensor.signal.pool.pool_3d()
>
> that would be better then using the 2d pooling to mimic 3d pooling.
>
> On W
do you want 2d or 3d pooling? We merged (today I think) a good interface
for pool 3d: theano.tensor.signal.pool.pool_3d()
that would be better then using the 2d pooling to mimic 3d pooling.
On Wed, Oct 12, 2016 at 8:12 AM, wrote:
> Hi Pascal,
> Input dimension is 5;
> problem fixed: I use pool_
Hi Pascal,
Input dimension is 5;
problem fixed: I use pool_2d code
thanks
On Tuesday, October 11, 2016 at 4:43:58 PM UTC+2, Pascal Lamblin wrote:
>
> Hi,
>
> The code throwing the exception is:
> > if x.type.ndim != 4:
> > raise TypeError()
>
> What is the number of dimensions of 'input'
Hi,
The code throwing the exception is:
> if x.type.ndim != 4:
> raise TypeError()
What is the number of dimensions of 'input' in your case?
Usually, the `pool_2d` helper function takes care of reshaping the input
if necessary, and passing correctly ws/ds to the underlying Op. Is there
any r
Hi Pascal,
in maxpool3d.py
I tried op = pool.Pool(ignore_border=False, mode='max', openmp=None)(input,
ws=(ds[1],ds[2]))
instead of op = pool.Pool((ds[1],ds[2]), ignore_border) that worked in the
previous Theano version.
This is the output :
Python 2.7.12 |Anaconda custom (64-bit)| (default
Hi Pascal,
in maxpool3d.py
I tried op = pool.Pool(ignore_border=False, mode='max', openmp=None)(input,
ws=(ds[1],ds[2]))
instead of op = pool.Pool((ds[1],ds[2]), ignore_border) that worked in the
previous Theano version.
This is the output :
Python 2.7.12 |Anaconda custom (64-bit)| (default,
On Sunday, October 9, 2016 at 5:01:04 PM UTC+2, Pascal Lamblin wrote:
>
> I think that parameter is now passed as an input to the node instead.
> So instead of Pool(ws, mode=..., ...)(input) you would need to do
> Pool(mode=..., ...)(input, ws=ws).
> This should work for pool.Pool as well.
>
I think that parameter is now passed as an input to the node instead.
So instead of Pool(ws, mode=..., ...)(input) you would need to do
Pool(mode=..., ...)(input, ws=ws).
This should work for pool.Pool as well.
On Sun, Oct 09, 2016, luca.wagner.0...@gmail.com wrote:
> Hi,
> I updated Theano to con
Hi,
I updated Theano to continue convnet3d test with float16, but running the
code I had an error in maxpool3d because the class Pool has fewer
parameters.
in the previous Theano version, class Pool had these parameters: ds,
ignore_border, st, padding, mode,openmp
in the latest Theano version c