index
:
demo.git
main
Vide-coded 64k demo system
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
training
/
train_cnn_v2.py
Age
Commit message (
Expand
)
Author
19 hours
CNN v2 training: Fix float64/float32 dtype mismatch in depth feature
skal
20 hours
CNN v2: Use alpha channel for p3 depth feature + layer visualization
skal
25 hours
CNN v2 training: Add --grayscale-loss option for luminance-based loss computa...
skal
26 hours
CNN v2: Change feature #6 from sin(10*x) to sin(20*y)
skal
26 hours
CNN v2: Add TODO for flexible feature layout in binary format v3
skal
26 hours
CNN v2: Add --mip-level option for parametric features
skal
30 hours
CNN v2 training: Use target image alpha channel
skal
30 hours
CNN v2: Restore per-layer kernel sizes support
skal
30 hours
CNN v2: Refactor to uniform 12D→4D architecture
skal
2 days
Refine training script output and validation
skal
2 days
TODO: 8-bit weight quantization for 2× size reduction
skal
2 days
TODO: Add random sampling to patch-based training
skal
2 days
CNN v2: Patch-based training as default (like CNN v1)
skal
2 days
Fix: CNN v2 training - handle variable image sizes
skal
2 days
CNN v2: parametric static features - Phases 1-4
skal