-
Hello.
Thank you for making this project.
I'm trying to index a short .wav file with the following python (2.7):
```
from SimpleAudioIndexer import SimpleAudioIndexer as sai
indexer = sai("..."…
-
https://arxiv.org/abs/1703.06857
> Deep Neural Networks (DNNs) have achieved remarkable performance on a variety of pattern-recognition tasks, particularly visual classification problems, where new…
-
Hi,
I was trying to reproduce the baseline performance of ConvNet (reported in your NIPS paper). But I tried the default setting (`cifar10_full_multistep_solver.prototxt`) as the provided one in th…
bobye updated
7 years ago
-
https://arxiv.org/pdf/1409.3215.pdf
-
Would there be a benefit to split long (30 seconds-ish) wav files to smaller ones? What is the optimum length for a wav file that is fed to Merlin?
-
Dear Friends,
Is the size of the output (the sequence of chars) of the model a deterministic function of the number of frames of the utterance?
Does the LSTM adapt the size of the output char se…
-
I'm trying to train my own neural net using dlib, so I defined my loss class and now I'm trying to test it. But I get some strange behavior: at first, I need to set initial learning rate to `1e-8` ins…
-
https://arxiv.org/pdf/1709.02656.pdf
https://arxiv.org/abs/1709.02656
-
Hi!
I'm currently trying to write a CMSSW module (slc6_amd64_gcc530, CMSSW_8_0_26_patch2) that uses the Python and NumPy C API's to load and evaluate Tensorflow graphs (https://gitlab.cern.ch/mrieg…
-
Hi
I am running CNTK for DNN training on machine with 2 identical GPUs. I am using mostly default values in config, but GPU utilization is not optimal. SamplesPerSeconds drops 7-8 times after each app…