Comments (9)
Indeed it works with 1.0.1 which is supposed to be a minor bugfix release over 1.0, and 0.4.1 is the last release before the 1.0 line, so I will go ahead and specify pytorch>=1.0 in the requirements.
from entmax.
Thank you for opening the issue. I'm having trouble replicating this but it sounds like a mismatch in between the dimensions of the input and the target. Could you provide an example that causes this bug?
P.S. This probably won't have any effect on the bug, but that version of pytorch is rather out of date.
from entmax.
Thanks.
After I switch to the most recent version, the error disappears. Seems like the function scatter_add_ has been updated.
from entmax.
@berlino you mean the most recent pytorch version?
We should try to bisect pytorch versions and figure out our minimum requirement, to list in readme. Reopening this until we figure it out.
from entmax.
(I suspect pytorch 1.0 is the minimum)
from entmax.
Sorry to ping you again @berlino,
We added a bunch of new features to the code and we're planning to make a package release on pypi soon, would you mind checking that your application works well with the current version of the code?
Some defaults were changed (dim=-1 now everywhere) and the import paths are now shorter (from entmax import sparsemax
for instance.)
from entmax.
No worries.
The updated version works well for my application. (I actually made similar changes when I used the code)
from entmax.
Thanks a lot! We will make a pypi release soon.
from entmax.
@vene Following this thread, I think pytorch should be specified as a dependency in the setup.py, assuming the environment does not have pytorch installed.
Currently, I ran into the problem "ModuleNotFoundError: No module named 'torch'" when I specify entmax as a dependency in my our own setup.py.
from entmax.
Related Issues (20)
- Usage of alpha HOT 3
- Unexpected behaviour of sparsemax gradients for 3d tensors HOT 8
- entmax implementation for Tesnoflow 2 HOT 1
- Replicating the behaviour from the paper HOT 1
- entmax_bisect leads to loss becoming nan HOT 16
- Problem with sparse activations HOT 9
- Entmax fails when all inputs are -inf HOT 1
- Alpha value less than one? HOT 8
- Index -1 is out of bounds HOT 1
- A bug when alpha = 1 for entmax_bisect? HOT 3
- `entmax_bisect` is not stable around `alpha=1` HOT 3
- Release patch 1.0.1 with torch install_requires fix HOT 5
- Code to reproduce figure 3 HOT 1
- alpha-entmax
- entmax_bisect bugs with fp16/bf16 HOT 1
- Nans gradients for tensors with singleton dimensions for budget_bisect. HOT 5
- Instability of entmax bisect around 0? HOT 1
- EntmaxBisect forward requires unused argument HOT 2
- Sparse losses return nan when there is -inf in the input 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 entmax.