Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Ellaft
/
multimodal-pc-fault-detector
like
0
arxiv:
2203.15332
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
multimodal-pc-fault-detector
/
src
132 kB
Ctrl+K
Ctrl+K
1 contributor
History:
17 commits
Ellaft
Update run_ablations.py: uses new train.py with Hub dataset + OGM-GE
1067497
verified
4 months ago
config.py
Safe
5.54 kB
Overwrite config.py with v2 config (OGM-GE params, asymmetric LR, auxiliary loss weights)
4 months ago
config_v2.py
Safe
9.25 kB
Add config_v2.py: OGM-GE hyperparameters + asymmetric LR config
4 months ago
dataset.py
Safe
8.35 kB
Add dataset, models, training, and ablation scripts
4 months ago
dataset_flexible.py
Safe
9.13 kB
Add flexible dataset module supporting custom HF audio and image datasets
4 months ago
dataset_real.py
Safe
6.36 kB
Add real dataset loader (ToyADMOS audio + MVTec AD visual)
4 months ago
dataset_v2.py
Safe
15.9 kB
Add dataset_v2.py: adapter for build_dataset.py output, drop-in replacement for dataset_real.py
4 months ago
models.py
10.8 kB
Overwrite models.py with v2 architecture (auxiliary heads + OGM-GE + anti-collapse)
4 months ago
models_v2.py
Safe
17.1 kB
Add models_v2.py: auxiliary heads + OGM-GE anti-collapse
4 months ago
run_ablations.py
3.41 kB
Update run_ablations.py: uses new train.py with Hub dataset + OGM-GE
4 months ago
run_ablations_v2.py
Safe
5.11 kB
Add run_ablations_v2.py: v2 ablation runner with OGM-GE experiments
4 months ago
train.py
16.8 kB
Overwrite train.py: defaults to Hub dataset (Ellaft/pc-fault-real-dataset), uses models.py + dataset_v2.py, OGM-GE enabled
4 months ago
train_v2.py
Safe
24 kB
Update train_v2.py: add --dataset flag to switch between old proxy data (dataset_real) and new built dataset (dataset_v2)
4 months ago