Comments (1)
Nevermind. After looking more carefully at the figure, and re-read the paper, I was able to reproduce it with the following code.
t = np.linspace(-3.0, 3.0, 100)
x = [[i, 0.0] for i in t]
x = torch.tensor(x)
softmax_y = softmax(x)
alpha125_y = entmax_bisect(x, 1.25)
alpha15_y = entmax_bisect(x, 1.5)
sparsemax_y = sparsemax(x)
alpha4_y = entmax_bisect(x, 4)
fig, ax = plt.subplots(figsize=(8, 6))
ax.plot(t, softmax_y[:, 0], label=r"$\alpha = 1$ (softmax)", linewidth=3, linestyle=':')
ax.plot(t, alpha125_y[:, 0], label=r"$\alpha = 1.25$", linewidth=2)
ax.plot(t, alpha15_y[:, 0], label=r"$\alpha = 1.5$", linewidth=3, linestyle='--')
ax.plot(t, sparsemax_y[:, 0], label=r"$\alpha = 2$ (sparsemax)", linewidth=3)
ax.plot(t, alpha4_y[:, 0], label=r"$\alpha = 4$", linewidth=1, color='k')
ax.set_yticks([0.0, 0.5, 1.0])
plt.legend()
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
- Tensorflow implementation of entmax1.5 HOT 10
- 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
- alpha-entmax
- Errors when using the loss function HOT 9
- entmax_bisect bugs with fp16/bf16 HOT 1
- Nans gradients for tensors with singleton dimensions for budget_bisect. HOT 5
- 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.