Comments (3)
denizyuret
commented on June 8, 2024
Outside of a @diff environment, Param(x) is designed to act like x for all
purposes. For example 2*Param(x) gives 2x, not Param(2x). I think the
current behavior of copy is consistent with this.
…On Sun, Nov 25, 2018 at 1:21 PM tscode ***@***.***> wrote:
When I copy a Param object, the result is not a Param, but its value.
Example:
copy(Param(1)) # returns 1 instead of Param(1)
Is this behavior intended? It was certainly surprising for me.
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#102>, or mute the thread
<https://github.com/notifications/unsubscribe-auth/ABvNpveFLGMN9SDO7uFdvV7dKQXEiuB_ks5uyt-LgaJpZM4Yx_vy>
.
from autograd.jl.
tscode
commented on June 8, 2024
Okay, makes sense. I hit this issue when I wanted to copy self-defined models in the obvious way, and implicitly expected that both the value and the optimizer of the param object would be copied. But this is of course easy to add by hand.
from autograd.jl.
NHDaly
commented on June 8, 2024
Fwiw, deepcopy(x) seems to still return a Param. I'm not sure if that's intended or not, but it's worth noting that it's different than copy.
julia> a = AutoGrad.Param( [1,2,3] )
>> 3-element AutoGrad.Param{Array{Int64,1}}:
1
2
3
julia> deepcopy(a)
>> 3-element AutoGrad.Param{Array{Int64,1}}:
1
2
3from autograd.jl.
Related Issues (20)
- grad doesn't work on trivial identity HOT 6
- bug in gradient with broadcast HOT 3
- cannot take derivative of a scalar function HOT 6
- Atom can’t evaluate a line which the regular REPL can
- Inside `@diff`, shouldn't `similar(Result{Array})` return `Result{Array}`? HOT 1
- mapslices and Param wrapped arrays
- Extend UngetIndex to multiple indices, values for efficiency HOT 1
- Autograd.Sparse type causes regression HOT 10
- getindex gradient collection bug
- Cannot `convert` an object of type UnitRange{Int64} to an object of type Colon
- Multiple functions sharing some gradients HOT 1
- Problems with grad after grad HOT 2
- Alkan bias add problem? HOT 1
- TagBot trigger issue HOT 2
- how to calculate gradient without calculating function outputs
- keyword args in broadcasted funcs not supported
- Param(x) as AbstractArray? HOT 1
- Incorrect derivatives when new arrays are constructed in computation
- AutoGrad and CUDA kernels HOT 1
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 autograd.jl.