NeuroDiffGym / neurodiffeq

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.
http://pypi.org/project/neurodiffeq/
MIT License
680 stars 89 forks source link

fixed h1_semi_norm loss function by converting gradient from list to … #144

Closed mecunha closed 2 years ago

mecunha commented 2 years ago

…tensor

codecov-commenter commented 2 years ago

Codecov Report

Merging #144 (72d6dfb) into master (add8b21) will decrease coverage by 0.24%. The diff coverage is 0.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #144      +/-   ##
==========================================
- Coverage   84.29%   84.05%   -0.25%     
==========================================
  Files          22       22              
  Lines        3521     3618      +97     
==========================================
+ Hits         2968     3041      +73     
- Misses        553      577      +24     
Impacted Files Coverage Δ
neurodiffeq/losses.py 58.82% <0.00%> (-3.68%) :arrow_down:
neurodiffeq/solvers.py 83.19% <0.00%> (-1.81%) :arrow_down:

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update add8b21...72d6dfb. Read the comment docs.