# Looking for pytorch method alternative in flux

**URL:** <https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360>\
**Category:** Machine Learning\
**Created:** [June 26, 2022, 2:07pm UTC](https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360 "2022-06-26T14:07:47Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![extremety1989](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/extremety1989/32/28184_2.png) [@extremety1989](https://discourse.julialang.org/u/extremety1989)\
**Post date:** [June 26, 2022, 2:07pm UTC](https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360/1 "2022-06-26T14:07:47Z")

</div>

i am looking for pytorch’s interpolate(out, scale\_factor=2, mode=“nearest”) [torch.nn.functional.interpolate — PyTorch 1.12 documentation](https://pytorch.org/docs/stable/generated/torch.nn.functional.interpolate.html)  
method alternative in Flux

---

<div class="post-metadata">

**Author:** ![jling](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/jling/32/212909_2.png) [@jling](https://discourse.julialang.org/u/jling)\
**Post date:** [June 26, 2022, 2:14pm UTC](https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360/2 "2022-06-26T14:14:54Z")

</div>

reference: [compatibility with Flux · Issue #396 · JuliaMath/Interpolations.jl · GitHub](https://github.com/JuliaMath/Interpolations.jl/issues/396)

---

<div class="post-metadata">

**Author:** ![CarloLucibello](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/carlolucibello/32/3278_2.png) [@CarloLucibello](https://discourse.julialang.org/u/CarloLucibello)\
**Post date:** [June 26, 2022, 2:36pm UTC](https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360/3 "2022-06-26T14:36:37Z")

</div>

probably you are looking for [NNlib.upsample\_nearest](https://fluxml.ai/Flux.jl/stable/models/nnlib/#NNlib.upsample_nearest) and Flux.Upsample for a corresponding layer

---

<div class="post-metadata">

**Author:** ![extremety1989](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/extremety1989/32/28184_2.png) [@extremety1989](https://discourse.julialang.org/u/extremety1989)\
**Post date:** [June 26, 2022, 3:05pm UTC](https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360/4 "2022-06-26T15:05:34Z")

</div>

this one does not work on Chain

---

<div class="post-metadata">

**Author:** ![extremety1989](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/extremety1989/32/28184_2.png) [@extremety1989](https://discourse.julialang.org/u/extremety1989)\
**Post date:** [June 26, 2022, 3:42pm UTC](https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360/5 "2022-06-26T15:42:10Z")

</div>

does it has the same effect as pytorch interpolate nearest ?

---

<div class="post-metadata">

**Author:** ![extremety1989](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/extremety1989/32/28184_2.png) [@extremety1989](https://discourse.julialang.org/u/extremety1989)\
**Post date:** [June 26, 2022, 4:56pm UTC](https://discourse.julialang.org/t/looking-for-pytorch-method-alternative-in-flux/83360/6 "2022-06-26T16:56:40Z")

</div>

i have tested, it works as expected thank you very much!