1156 downsampling experiment #1165
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
spigo900
requested changes
Aug 17, 2022
spigo900
approved these changes
Aug 18, 2022
added 8 commits
August 18, 2022 15:19
Note that the confidence score is not set on a per-decode basis here since we currently do not alter confidence values with GNN decodes in ADAM.
sidharth-sundar
force-pushed
the
1156-downsampling-experiment
branch
from
558ae62 to
2d84db2
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Closes #1156 and #1157
Performed both within the same branch because I needed similar scripts for both for visualizing GNN/ADAM performance between different experiments.
There are 4 important features added here:
kGNN decodes per object fromshape_stroke_graph_inference.pykdecodes as a node in ADAM and handle accordingly.Aside from those, most of the new additions here are just adding parameter files which I used the preexisting downsample/unknown object generation scripts to create the curricula for.