Comments (4)
avik-pal
commented on June 9, 2024
1
(frog::LeapFrogCustom)(x,ps,st) = (frog.sub_net(x[1],ps,st)[1] .+ x[2],x[1]),st
See the broadcasted addition. That makes the code type inferrable (Not sure why, though).
Regardless if you use Cthulhu, it tells you exactly where the problem is.
from lux.jl.
arthur-bizzi
commented on June 9, 2024
Interestingly, a single LeapFrog Layer containing a Chain also works fine. The problem seems to be chaining custom layers containing Chains.
from lux.jl.
avik-pal
commented on June 9, 2024
Can you try changing frog.sub_net(x[1],ps,st)[1] to first(frog.sub_net(x[1],ps,st))? The first one might cause type instability, since you are indexing into a heterogeneous container.
from lux.jl.
arthur-bizzi
commented on June 9, 2024
Tried it, no difference.
from lux.jl.
Related Issues (20)
- Documentation Enhancement Suggestions HOT 1
- @save not defined? HOT 1
- The MNIST Neural ODE example does not work with `ReverseDiffAdjoint` HOT 6
- Update Documentation to mention loading AD Packages for Training HOT 4
- `ComponentArrays` makes coupling layers type-unstable unexpectedly HOT 2
- Custom Layer, Differential Equation as Activation Function. HOT 4
- Gradients of shared parameters do not behave as expected HOT 1
- inconsistent LSTM results in time series forecast between Flux.jl and Lux.jl
- Broadcast Layer
- Can't use freeze with ComponentArray. HOT 2
- `Lux.testmode` resorts to scalar indexing with frozen params HOT 2
- Custom Model for Neural ODE HOT 1
- Periodic Padding HOT 1
- Export trained model for Tensorflow/PyTorch/C++? HOT 2
- Bug in `ConvTranspose`? HOT 1
- Generating Parameters with CUDA HOT 2
- Zygote gradient fails for Custom Layer HOT 2
- Adaptors should **not** change the dtype HOT 1
- Any equivalency to torch.nn.Parameter? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lux.jl.