Hi!
I'm new to Theano. Currently I use Lasagne to train a neural network and I
notice that there is no mean-image computation.
According to this course : http://cs231n.github.io/linear-classify/,
calculation of mean image is neccesary before training. Is it true or not?
It true, does Theano h
Or maybe simpler, use hdf5 file format. There is the pytables Python
package that support it. It will ask an numpy array, but will load the
element you select efficiently.
Le 15 sept. 2016 13:03, "Kyle Kastner" a écrit :
> This is not really Theano specific, but I write Python iterators to
> han
Hi guys
Thx for the suggestions. I ended up using HFD5. There is some nice
framework also that uses it called Fuel. So far looks pretty good. Thx
again.
On Friday, September 16, 2016 at 3:30:49 PM UTC+2, nouiz wrote:
>
> Or maybe simpler, use hdf5 file format. There is the pytables Python
> pa
Theano don't do that for you automatiacally. Normally, people does that
durig the pre-processing step of the dataset.
But if you have the stats, you could do it during the theano function call
if you want.
Fred
On Fri, Sep 16, 2016 at 3:25 AM, T Nguyen
wrote:
> Hi!
>
> I'm new to Theano. Curre
This isn't really a theano question and might get more traction elsewhere.
Have you considered adding a "no action" class to your problem for the
frames/times where nothing is happening?
On Thursday, September 15, 2016 at 8:15:01 AM UTC-7, aditya vora wrote:
>
> Hello ,
>
> We are training a 3D
Hi there,
I have been reading the documentation as well as the discussion on using
float16 instead of float32 to reduce memory footprint on a single GPU.
My task is to train a 3D convolutional neural network which has a large
memory footprint (as a result of the feature cubes and their gradient
To say the conclusion first, I want to check shape of variable 'X' that is
'sequences' parameter in theano.tensor.scan function
scan function looks like this :
def forward(self, X):
"""
X.shape = (timesteps, dim)
X.shape = (n_samples, timesteps, dim)
"""