Comments (4)
Definitely! L1 and MSE for sure. I would also add a binary cross entropy as well.
We already started a loss module here but it has no docs yet.
Some testing + docs for any additional losses would be fantastic.
Also, what's the distinction between the nll_loss and the cross_entropy loss we already have?
from mlx.
Hi, I'll implement the L1 and MSE losses in that case, and you are correct about the negative log likelihood! I was just going through the pytorch losses and thinking about which would be the most helpful to add. Of course I'll add docs and testing aswell.
from mlx.
There have already been contributions for L1 and MSE. You can see the referenced PRs in this issue to see what's been/being added.
If there are other common losses you'd like to add, feel free to let us know and we can discuss here.
from mlx.
All the losses in this issue have been pushed to main so I will close it. Feel free to open a new issue for new losses.
from mlx.
Related Issues (20)
- Does mlx support Apple m chip npu HOT 1
- `sorted` and `argSort` don't work for split arrays HOT 1
- Large ops with multiprocess fail with internal error HOT 3
- [Feature Request] support dtype in mlx.core's module initialization HOT 1
- [BUG] NaN when using max reduction + compile HOT 1
- [Feature] Metal inverse (`mx.linalg.inv`) HOT 4
- [BUG] Missing types HOT 6
- [BUG] Typo: traditinoal -> traditional
- [Feature] cross product HOT 1
- Sample packing using mx.fast.scaled_dot_product_attention? HOT 1
- [Feature] Make APIs non-blocking HOT 3
- [Feature] Enable Metal argsort, sort for > 2M elements along an axis
- [Feature] searchsorted HOT 4
- [Feature Request] Support convolution backward for groups > 1. HOT 1
- [BUG] 'mlx.core.linalg.qr' doesn't work on gpu, there's an abort. HOT 1
- [BUG] HOT 8
- [BUG] type stubs are missing for python 3.9 and 3.10 distributions
- [Feature Request] Adding option to follow PyTorch API in GELU initalization HOT 1
- [BUG] Segmentation fault while running custom operations HOT 4
- Memory Leakage Issue in MLX 0.16 HOT 9
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 mlx.