haoyangz

Memory explosion

9

I was tuning a mid-size network. I observed that the memory usage kept rising and with enough trials (around 50) eventually it caused the server to kill it for taking...

Can data and model function take argument?

2

It would be nice if they can so that I could pass argument (such as file path) from outside of the function, rather than manually changing the file every time...

Softmax or logsoftmax for auxiliary prediction

1

The current code uses softmax for auxiliary prediction and during training uses NLL Loss. But according to [here](http://pytorch.org/docs/master/nn.html) it seems that the right last layer to go with NLL is...

--use-nonoverlapping-peaks argument never used

1

It seems that the argument `--use-nonoverlapping-peaks` is never used. Instead, the code checks for an argument "--use_nonoverlapping_peaks". When I corrected this and ran it on two replicates where there are...

Limit running time / jobs proposed

1

To make caffe-with-spearmint into a fully automated pipeline of hyper-parameter selection, training and testing, it seems to be necessary to make it possible to control the running time or the...

Error when I have more than two classes

4

Hi, I was trying to change the code to use on classification task where there are more than two classes of outputs (positive and negative). I changed **preprocess.py** and it...