-
I am using a 1070 and 8GB graphic card, and I still get the OOM resource exhausted method in between training a mnist for default configuration. I even Reduced the batch sizefrom 32->16->8 , can you h…
-
Hi Chris,
nice package and thanks for the swift reply last week!
I have modified the neuro ODE example to regress a simple affine function y = 1-x/x_0 (here x_0 = datasize-1). I found that the neu…
-
I'd like to prototype DiffEqFlux with Zygote, which will have a much nicer API and generally improve all the things. However, to do that we need to make DiffEqSensitivity a but more flexible in terms …
-
I have tried to run the example in the README however `diffeq_rd()` throws a BoundsError [error message attached](https://github.com/JuliaDiffEq/DiffEqFlux.jl/files/2861990/diffeq_rd_error_message.txt…
-
Data:
- take data from groomer W, QCD, top.
- add quark and gluon data.
- add DELPHES level for all datasets (detector simulation)
Model:
- generate tree structure (D, kt) -> (Dhard, kthard, Ds…
-
Hello, I'm trying to re-implement the part of the paper about modeling an inhomogeneous Poisson process, however I don't see how the compensator (negative part of the likelihood) can be computed "in a…
-
First of all, thanks for publishing this very interesting package!
I am trying to use this to do some backprop through an ODE where my parameters are matrices rather than a collection of scalars, a…
-
Our README specifies two commands for running our ETL process.
Currently, they are:
```
./arxiv_as_a_newspaper -run-etl-process
```
and
```
./arxiv_as_a_newspaper -write-etl-results-to-file …
-
Hi, I'm trying to play with Neural ODEs and do some reimplementations in Tensorflow.
I was able to implement basic solver which works with the spiral problem in your examples.
However, I got stuck…
-
the sequel of neural ODE, the JJFORD, has been released out, which seems interesting. I wonder if you are interested in its implementation?