-
Hi, everyone.
I'm trying to run GoogLeNet with Batchnormalization, but it is not fast enough.
My implementation is here. (I have to write some scripts to read/writes images and learning rate schedu…
-
## Independent Variables
In rough order, we want to sweep each of the following variables:
To evaluate the model behavior:
- [x] h in MCD in both streaming and batch (e.g., 1, .95, .75, .5, .25, .1,…
-
I posted this on the users group and a responder said it may be useful here.
valgrind will complete if leveldb is used instead of lmdb.
Compiled with GPU and run with GPU
==4315== LEAK SUMMARY:
==43…
-
Hey guys,
I was wondering how are the initial internal states in a recurrent layer dealt with? So far it appears they are reset are every run. Is there any way to preserve them?
I'd like to be able …
-
Hello,
I am quite new to Keras, I am wondering how keras could extend my pre-processed inputs.
My case is similar to a "sentiment analysis". what I have is large english corpus labeled with their "se…
-
Are there more implementations of disaggregation algorithms that we can play with apart from the ones that come with nilmtk (hart85, co, fhmm_exact)?
I'm particularly interested in how the [neural ne…
-
layers.py, on which most of the nntools code is based, has always been geared towards feed-forward neural networks. We should look into recurrent neural networks as well. Personally I don't have a lot…
-
Sorry if this should really go to the julia-users mailing list. But it is easier to at authors of existing packages here on github. I want to initiate the discussion of the possibility of creating a J…
-
Since reversePush is not tail recursive, it results in a stack overflow for even simple networks when you push in a lot of data/use a bunch of memory. Here's the code I used to produce this (backprop …
-
We're getting close to the finish line, so I think we should tie all our work to something in the report or grading rubric (and actually start writing sections of the report). Here is everything that …