jaredleekatzman

The data-loading API for the parameter search isn't that fleshed out. The dataset parameter you provided 'whas' isn't understood by the script. You need to instead specify the location of...

The learning rate box constraint is actually on a log scale. So it is searching between 10e-7 to 10e-3. > On Jan 21, 2018, at 9:19 PM, Charlotte wrote: >...

I agree with @dareneiri , it's hard to debug without knowing the code that you used to generate this error. My guess from the line `ValueError: shapes (234,6) and (10,10)...

If you run `import lasagne` outside of deep_surv, does that work? Or does it only not work from when you run `import deep_surv`

Are you still having this issue? It looks like the logger is being passed from the .train() function to the _get_train_valid_fn() which is then passing it up update_fn through the...

Sorry for the confusion, the default parameters are place holders and are not meant to produce a working network. I am not able to suggest parameters as optimal parameters are...

@LeZhengThu could you provide more context? Did you train the network? Is it performing well on a validation set?

Hi, I am currently working on releasing the Optunity script so that people can run their own hyper-parameter search. I hope to have it done soon. > On May 24,...

@dareneiri Sorry for the delay, but I've uploaded the script I used to run a random hyper-parameter search under the directory `hyperparam_search/`. If you still need to use it, let...

Are you still facing the issue? This is because the 'adadelta' updater isn't implemented in the utils function: [here](https://github.com/jaredleekatzman/DeepSurv/blob/master/deepsurv/utils.py#L63-L71). So the function is returning "None". If you can update the...