-
Hi,
I have created a simple model consisting of two 1-layer nn competing each other. So, I have my own loss function based on those nn outputs. It is very similar to GAN. The problem is that for a v…
-
The linesearches we implement should not test for strict function decrease (fnew
-
For those already running [Neural-Style](https://github.com/jcjohnson/neural-style), and/or similar projects, many of the dependencies are already setup.
When running `git clone`, the `gen_laplaci…
-
I'm fitting my data about 50 csv files but Prophet crashes and throwing runtime errors. This only happened when I switched to Ubuntu 16. On Windows, prophet runs without error.
`Optimization termin…
-
I can't get the augmented lagranian algorithm to work because the gradient vector seems to be empty
```
opt = Opt(:LD_AUGLAG, 1)
maxeval!(opt, 1)
ftol_abs!(opt, 1e-3)
opt2 = Opt(:LD_LBFGS, 1)
…
-
# The error is as follow:
16/04/19 18:47:35 ERROR LBFGS: Failure! Resetting history: breeze.optimize.FirstOrderException: Line search zoom failed
16/04/19 18:49:18 ERROR LBFGS: Failure again! Giving …
-
This error occurs when running `py.test`, but not `nosetests`. The current testing framework is `nosetests`, but it would be best to switch testing frameworks since `nosetests` is no longer maintained…
-
Currently, the implementation of `bfgs` isn't always converging, and the implementation is messy. Should we spend some time working on this, or toss it? If we're going to keep it, what exactly is go…
cicdw updated
7 years ago
-
In order to simplify slightly the API, I would vote for removing the `"auto"` value of `acq_optimizer`.
I am not convinced we should default to random sampling as soon as one of the dimensions is…
-
Hello, it's me again :-)
Unfortunately the compiled `libcuda_utils.so` is still not working as intended.
When i import it via torch:
```
th
______ __ | Torch7
/_ __/__ …