mikeinnes / zygote-paper Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
Hello,
very nice article. If I run line 40 of neural_sde.jl:
p1 = plot(monte_nsum, title = "Neural SDE: Before Training")
I get the following ERROR:
ERROR: LoadError: Cannot convert Tuple{Array{Float64,1},Array{Float64,1}} to series data for plotting
Thank you
On the arXiv version of this paper, there's a missing citation:
... Monte Carlo sampling where appropriate (sections 3.6, ??).
Maybe add a readme like so:
# Zygote paper
## Running examples
Clone the repository and instantiate the environment:
```julia-repl
julia> cd("path/to/cloned/repo")
(v1.3) pkg> activate .
(v1.3) pkg> instantiate
```
Then you can use `include` to run specific examples:
```julia-repl
julia> include("neural_sde/neural_sde.jl")
```
Also when running the steps above, I got
julia> include("neural_sde/neural_sde.jl")
[ Info: Precompiling Flux [587475ba-b771-5e3f-ad9e-33799f191a9c]
ERROR: LoadError: ArgumentError: Package DiffEqFlux not found in current path:
- Run `import Pkg; Pkg.add("DiffEqFlux")` to install the DiffEqFlux package.
Stacktrace:
[1] require(::Module, ::Symbol) at ./loading.jl:887
[2] include at ./boot.jl:328 [inlined]
[3] include_relative(::Module, ::String) at ./loading.jl:1105
[4] include(::Module, ::String) at ./Base.jl:31
[5] include(::String) at ./client.jl:432
[6] top-level scope at REPL[4]:1
in expression starting at /Users/tlienart/Desktop/zygote-paper/neural_sde/neural_sde.jl:1
There's no *toml
file in that repo and the main Project.toml file is missing DiffEqFlux
, StochasticDiffEq
and DiffEqMonteCarlo
afaict)
The Whedon checklist JuliaCon/proceedings-review#55 kindly requires some OSI approved license.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.