lixiaohui
33f75f191c
Fixbug: fix API docs bugs
5 years ago
lixiaohui
f6134bd1da
fixbug: NaiveFaithfulness NaN warning and system errors when benchmark num_labels and model output dimension does not match.
5 years ago
YuhanShi53
ca353c3262
fix get_next bug in explainer._runner and NaN dataset.
5 years ago
YuhanShi53
c24fabcd8e
correct mistakes in docstring and fix bugs when no benchmark is passed.
5 years ago
YuhanShi53
1c4ab31231
fix mistakes in docstring
5 years ago
mindspore-ci-bot
467a0983b4
!8962 [fixbug] issue#I26THC: ValueError when argument 'benchmarks' is set default
From: @lixiaohui33
Reviewed-by: @wuxuejian,@ouwenchang
Signed-off-by: @ouwenchang
5 years ago
lixiaohui
9f722fb850
fix issue#I26THC: ValueError when benchmark is set default
5 years ago
YuhanShi53
61164e7d52
add feature/explainer/ClassSensitivity, Occlusion, Robustness
5 years ago
lixiaohui
2161c85d52
add rise explanation method, modify runner and faithfulness
5 years ago
unknown
64f27b66f1
add uncertainty, 1 ch saliency, separated datafile
bugfix
undo unexecpted changes
modify summary format
bugfix
fix CI problem
enhance comment
fix comment typo
use mindspore.log for errors
fix pylint issues
5 years ago
lixiaohui
df94bb6562
Fix issue#123FX6: format API comments
5 years ago
lixiaohui
5ed0766a80
Fixbug: Numpy warning during correlation calculation when all zero saliency map encountered
5 years ago
lixiaohui
1632d44711
fix benchmark=[] bug
5 years ago
lixiaohui
fbb88530cd
Fixbug: add input params validity check & fix NaN faithfulness issue
5 years ago
lixiaohui
c8b62074c9
include explainer in cmake and modify __init__ in explanation classes.
5 years ago
lixiaohui
744f094add
Add explainer to provide eXplainable AI tools.
This commit provides APIs for user to use the widely used attribution methods to explain DL models and the evaluation methods to quantify the explanations. With combination of MindInsight, the user can have a friendly visualization on their models.
5 years ago