-
Hi Robert,
I've rendered some Eidolon Distortions, but I used the MATLAB equivalent version instead of the python one (which seems like you used to render the stimuli). I have all they hyperparameter…
-
Hi
I want to train a HOG+SVM detector in OpenCV and then use your library for acceleration. Does it support both HOG and SVM?
-
Proper fitting of models to old and new dev split. Right now hyperparameters are shared, which might be bias heavily results.
For each model tune learning rate and l2 regularization.
-
## Issue description
when it use torch._C._nn.upsample_nearest2d(input, _output_size(2)), it's comes with
RuntimeError: CUDA error: invalid configuration argument.
The problem is only occu…
-
Hi,
I am just curious. In your document, you specify that:
+ PS: do gradient reduction
+ Worker: apply gradient update
So does it mean that each worker should hold all the parameters ?
-
I have set up a pipeline using Scikit-learn. It works well with Scikit-learn's models. I'd like to try using DNNs now. My pipeline makes heavy use of Pandas' DataFrames and modifying it to use NumPy's…
-
Is there a makefile that I can use?
-
Hi!
l think Eran is great after l used it a lot.
But l have met some problems when l use it.
First, if my network has the Sigmoid activation in the last layer it will occur an error. Should the c…
-
We need the following:
* A build server
* A temporary public-facing server to display results
I can run this with my Jenkins server and output it to an S3 site or my server as a static site. Th…
-
Example:
```kotlin
val model : MultiLayerNetwork = ...
val epochitTr = MultipleEpochsIterator(5, trainData)
model.addListeners(object: BaseTrainingListener(){
override fun onEpochStart(mode…