folivo/PINA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improve conditions and refactor dataset classes (#475)

Browse Source 
* Reimplement conditions

* Refactor datasets and implement LabelBatch

---------

Co-authored-by: Dario Coscia <dariocos99@gmail.com>
This commit is contained in:
Filippo Olivo
2025-03-07 11:24:09 +01:00
committed by Nicola Demo
parent bdad144461
commit a0cbf1c44a
40 changed files with 943 additions and 550 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
pina/problem/zoo/supervised_problem.py
View File

@@ -8,7 +8,7 @@ class SupervisedProblem(AbstractProblem):
A problem definition for supervised learning in PINA.
This class allows an easy and straightforward definition of a Supervised problem,
based on a single condition of type `InputOutputPointsCondition`
based on a single condition of type `InputTargetCondition`
:Example:
>>> import torch
@@ -31,7 +31,5 @@ class SupervisedProblem(AbstractProblem):
"""
if isinstance(input_, Graph):
input_ = input_.data
self.conditions["data"] = Condition(
input_points=input_, output_points=output_
)
self.conditions["data"] = Condition(input=input_, target=output_)
super().__init__()