andrea

Checkpoint callbacks with n_jobs > 1

6

I would to use gridsearchcv in parallel mode. However, I think that the checkpoints used during the trainings in the different processes could override each other between them since they...

[request] logout window

1

Is possible to personalize the logout window with something like old win95 style? for example http://dmf.unicatt.it/~mrz/pc/images/w95close.gif

request: epochs numbers to converge in readme.md

1

Is possible to know how many epochs are needed to reach the reported results?

Is it possible to know in what the cifar10 version reported in the repository differs from the original one?

hi all! the code needs to execute EdgeDetectTest.exe , so it needs Windows SO. Is there a workaround or can anyone give the exe source code so that I can...

is it possible to obtain a negative value of distance e.g. Category:Art rock musical groups Category:Houses completed in 1800 SRMetric sr = configurator.get(SRMetric.class, "category","language", en.getLangCode()); I obtain a value of...

int id2=pageDao.getIdByTitle("Category:Islamic terrorism",simple,NameSpace.CATEGORY); Collection categoryList = localCategoryMemberDao.getCategoryIds(en, id2); for(Integer e: categoryList) { System.out.println(e); System.out.println(pageDao.getById(simple, e)); } gives me 33049350 LocalPage{nameSpace=CATEGORY, title=Category:Islam and violence (en), localId=33049350, language=English} 16702064 LocalPage{nameSpace=CATEGORY, title=Category:Islamic fundamentalism...

when I use padding='same' in conv2d layers i get error. basic example: m = Sequential() m.add(Conv2D(512, kernel_size=(3, 3), activation='relu', padding='same', input_shape=(14,14,512),strides=(1,1))) m.add(MaxPooling2D(pool_size=(2,2))) m.summary() explainer = LRP(m) exp = explainer.explain(numpy.ones((14,14,512)), 3)[0]...

If I ask for an explanation on a model with softmax as last layer i get: LayerNotImplementedException I think it can be easily removed simply not considering the last softmax...