-
Hi,
I'm trying to train with dropout a DNN of 6 sigmoid-based hidden units for speech recognition purposes.
I'm using the following command:
`$cn_gpu configFile=${expdir}/Base.config configFile=${ex…
-
The creators of Deep Neural Decision Forests [1] implemented their networks in DMLC/CXXNET which has been superseded by this project. It is much more efficient to estimate the leaf node probability di…
-
The current Schematics is very eager to insert default values at every turn:
``` python
class Foo(Model):
s = StringType(default='blah')
```
``` python
>>> f = Foo()
>>> f._data
{'s': u'blah'}
`…
-
For many applications, 32 bit floating point numbers are sufficient. Using them improves speed because of the memory throughput and 32 bit SIMD operations. Can we have a dense matrix that uses 32 bit …
-
Hi all,
I am working on a project where I have to perform a prediction of a sequence of real coefficients (normalized) based on an input sequence of vectors containing categorical and real values (i.…
-
Need documentation , especially for compound types. I didn't know they even exist until i read the code.
-
Hi Admin,
Do you have any plan to create a documentation or tutorial on How to use deepy?
I would like to contribute.
Please let me know.
Thanking You.
-
It seems that the documentation hasn't updated in a while, according to https://readthedocs.org/projects/schematics/
Despite my merged PR from yesterday, the documentation hasn't changed:
- Github li…
-
It seems like building a dnn learner using the learnerX method with `addConstFeat=true` doesn't actually add a constant feature.
```
val (nn,opts)= DNN.learnerX(indir+"trainData%03d.smat.lz4",indir+…
-
All the compound types define both `export_loop` and `to_primitive` methods, but `to_primitive` never seems to be called.
Am I right in assuming that, for compound types, `to_primitive` is just a his…