Comments (5)
Yes, I just tested that. I only need the stack at the end to allow a Dense
layer to take in the output. So:
Chain(
Recurrence(RNNCell(inputsize => latentsize); return_sequence=true),
Recurrence(RNNCell(latentsize => latentsize); return_sequence=true),
:
x -> stack(x; dims=2)
)
works.
from lux.jl.
I will take a closer look at this, but I think we can just use Chain. If we can use a chain, we should just add a note in the manual
from lux.jl.
Chains of this type work:
Chain(
Recurrence(RNNCell(inputsize => latentsize); return_sequence=true),
x -> stack(x; dims=2),
Recurrence(RNNCell(latentsize => latentsize); return_sequence=true),
x -> stack(x; dims=2)
:
)
from lux.jl.
You might not need a stack here I think. Recurrence should be able to take a VectorOfArray input (this was one of the reasons to not stack the outputs by default)
from lux.jl.
So just a note in the documentation is good enough for this.
from lux.jl.
Related Issues (20)
- Meta Issue for proper Enzyme Integration into Lux HOT 3
- Meta-Issue for improvements to `@compact`
- Rework ChainRules for DynamicExpressions HOT 1
- Nested AD for Parameter Gradient/Jacobian HOT 7
- Pullback over twice jacobian HOT 9
- Rewrite `@layer_map` to use KeyPath from Functors
- Extracting part of a model, with the corresponding parameters and states HOT 1
- Serializing/Deserializing Lux Models
- Differentiating `Zygote.pullback` HOT 9
- Batched Jacobian Functions
- Error for JVP by Enzyme HOT 16
- [Nested AD] Incorrect gradient when taking a gradient over a gradient using StatefulLuxLayer HOT 7
- batched_jacobian + CUDA => InvalidIRError HOT 2
- Add a compiled tape version for ReverseDiff
- SimpleChains integration doesn't work with Enzyme HOT 3
- Simple MLP requires Enzyme runtimeActivity HOT 2
- Using `swish` as `Conv` activation function errors on the GPU HOT 1
- Fast activation error HOT 1
- Definition and implementation of 'Loss' in Linear Regression Tutorial "Julia & Lux for the Uninitiated" HOT 2
- Add improper qualified accesses checks
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.