search

byu-dml / d3m-dynamic-neural-architecture

1 stars 1 forks source link

attention models use features per head param #164

Closed bjschoenfeld closed 5 years ago

bjschoenfeld commented 5 years ago

closes #162

codecov-io commented 5 years ago

Codecov Report

Merging #164 into develop will increase coverage by 0.02%. The diff coverage is 0%.

Impacted file tree graph

@@             Coverage Diff             @@
##           develop     #164      +/-   ##
===========================================
+ Coverage    57.24%   57.26%   +0.02%     
===========================================
  Files           33       33              
  Lines         2203     2202       -1     
===========================================
  Hits          1261     1261              
+ Misses         942      941       -1
Impacted Files Coverage Δ
dna/models/torch_modules/dag_attention_mlp.py 30.76% <ø> (ø) :arrow_up:
dna/models/dag_attention_regression_model.py 38.88% <ø> (ø) :arrow_up:
dna/models/torch_modules/attention_mlp.py 29.72% <0%> (+0.78%) :arrow_up:
dna/models/attention_regression_model.py 33.33% <0%> (ø) :arrow_up:

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 781c24c...0dc801b. Read the comment docs.