Machine-Learning
/
AIIA
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: Machine-Learning:6d8eeb2011ca7aa86c821b3c19e5ad8ec218e5ed
Branches Tags
Machine-Learning:main
..
compare: Machine-Learning:2eee8732479ac4fcf8e42b00bfa34c45cd97f298
Branches Tags
Machine-Learning:main

2 Commits
6d8eeb2011 ... 2eee873247

Author SHA1 Message Date
Falko Victor Habel 2eee873247 Merge pull request 'gates where not saved as well' (#25) from bug_fixes into main 
Reviewed-on: #25
 2025-03-03 18:02:00 +00:00
Falko Victor Habel 35edadf727 gates where not saved as well 2025-03-03 19:01:29 +01:00
1 changed files with 2 additions and 2 deletions
Show Stats Expand all files Collapse all files

4
src/aiia/model/Model.py
View File

@ -193,8 +193,8 @@ class AIIAmoe(AIIA):
# To generate gating weights, we first need to determine the feature dimension. # To generate gating weights, we first need to determine the feature dimension.
# Each expert is assumed to return an output of shape (B, C, H, W); after averaging over H and W, # Each expert is assumed to return an output of shape (B, C, H, W); after averaging over H and W,
# we obtain a tensor of shape (B, C) where C is the number of channels (here assumed to be 410). # we obtain a tensor of shape (B, C) where C is the number of channels (here assumed to be 224).
gate_in_features = 410 # Adjust this if your expert output changes. gate_in_features = 512 # Adjust this if your expert output changes.
# Create a gating network that maps the aggregated features to num_experts weights. # Create a gating network that maps the aggregated features to num_experts weights.
self.gate = nn.Sequential( self.gate = nn.Sequential(