Skip to content

Remove Input Channel #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 25 commits into
base: dev
Choose a base branch
from
Draft

Remove Input Channel #11

wants to merge 25 commits into from

Conversation

aditya0by0
Copy link
Member

@aditya0by0 aditya0by0 commented May 28, 2025 •
edited
Loading

aditya0by0 added 24 commits May 7, 2025 16:18
@aditya0by0
Create .gitignore
9150bb6
@aditya0by0
update precommit + github action
06a71a6
@aditya0by0
pre-commit format files
ff1adc9
@aditya0by0
change graph from directed to UNDIRECTED
d7f30d3
@aditya0by0
add test data
b8189d1
@aditya0by0
edge_features should be calculated after undirected graph
ad301e6
@aditya0by0
directed edge which form an un-dir edge should be adjancent
344d828
@aditya0by0
add test for GraphPropertyReader
8a69828
@aditya0by0
add gt test data for aspirin
e0064b8
@aditya0by0
Update test_data.py
a9c7228
@aditya0by0
add more graph test
0a9760d
@aditya0by0
first src to tgt edges then tgt to src
1a8dcb6 
- instead of using adjacent directed edge, this one is better approach since we can stack edge attributes generated later without any further logic to rearrange edge_attr
@aditya0by0
add test for duplicate directed edges
5d4c174
@aditya0by0
restore import
945ef7c
@aditya0by0
concat edge attr for undirected graph
53a240a
@aditya0by0
concat prop values instead of edge_attr
b1f2da3
@aditya0by0
Merge branch 'dev' into fix/directed-to-undirected-graph
3615fb1
@aditya0by0
Merge branch 'dev' into fix/directed-to-undirected-graph
7a8b664
@aditya0by0
inherit from ChebiOverX
53ca438 
instead of Base data module, as `load_processed_data_from_file` method used in this class is available in Dynamic dataset class
@aditya0by0
nan_to_num numpy2.x compatibility
4319e47 
fix for #10
@aditya0by0
add print statements
7c0a484
@aditya0by0
remove print for dataloader phase
ffc0b75
@aditya0by0
Update .gitignore
0a39749
@aditya0by0
why input channels needed? when n_atom_properties is there
51e609e
@aditya0by0 aditya0by0 self-assigned this May 28, 2025
@aditya0by0 aditya0by0 requested a review from sfluegel05 May 28, 2025 18:57
@aditya0by0 aditya0by0 linked an issue May 28, 2025 that may be closed by this pull request
Clarify and Fix Usage of Input Channels in Convolution Layers #12
Open
@aditya0by0 aditya0by0 added the bug:fix fix for bug label Jun 5, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@sfluegel05 sfluegel05 Awaiting requested review from sfluegel05

Assignees

@aditya0by0 aditya0by0

Labels
bug:fix fix for bug
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Clarify and Fix Usage of Input Channels in Convolution Layers
1 participant
@aditya0by0