unit8co/darts

Dirichlet Likelihood TFT model

Open

#1,813 opened on Jun 3, 2023

View on GitHub
 (6 comments) (0 reactions) (0 assignees)Python (762 forks)batch import
buggood first issue

Repository metrics

Stars
 (6,832 stars)
PR merge metrics
 (Avg merge 143d 16h) (16 merged PRs in 30d)

Description

Hello, I'm tring to use DirichletLikelihood in TFT model, but I got this issue. How can I fix it?

`ValueError: Expected value argument (Tensor of shape (32, 12, 1)) to be within the support (Simplex()) of the distribution Dirichlet(concentration: torch.Size([12, 1])), but found invalid values:
tensor([[[0.5691],
         [0.8910],
         [0.6211],
         [0.0000],
         [0.3685],
         [0.3022],
         [0.5626],
         [0.3967],
         [0.6753],
         [0.6197],
         [0.4106],
         [0.6041]],
...
        [[0.0000],
         [0.0000],
         [0.0000],
         [0.0000],
         [0.0000],
         [0.0000],
         [0.4241],
         [0.3950],
         [0.3232],
         [0.2716],
         [0.3947],
         [0.2650]]])`

Thanks

Contributor guide

Research direction
Examine the input tensor shape and verify that the values are normalized to sum to 1 across the simplex dimension. Check if a softmax layer is missing or if the concentration parameter shape aligns with the expected input.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
PythonPyTorchbasic understanding of probabilistic models
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40