933 MB

Ctrl+K

1 contributor

History: 30 commits

JonathanFhima

Remove weights/model.yaml - superseded by the single root config.yaml

284a8d9 verified 34 minutes ago

pvbm
Rehost PVBM optic-disc-segmenter weights (Google Drive link was broken/rate-limited) about 11 hours ago
weights
Remove weights/model.yaml - superseded by the single root config.yaml 34 minutes ago
.gitattributes

1.75 kB
Add Table 4 (pretraining/generation ablation) about 21 hours ago
LUNetv2.py

2.87 kB
Trim dead training-only code paths (loss-alpha bookkeeping, unused random-init branch, dead pre_load_model checkpoint-surgery block, unused imports) - none of it executes for inference; verified via strict safetensors load + identical forward-pass output 34 minutes ago
README.md

5.23 kB
Link the RLAD + PVBM end-to-end tutorial about 10 hours ago
benchmark_examples.png

659 kB
xet

Replace AV-WIDE example with a better-lit source image (the old one was nearly black, vessels looked like they were floating on nothing) 43 minutes ago
config.yaml

173 Bytes
Add root-level config.yaml so HF Hub counts downloads (its default download-tracker only watches config.json/config.yaml/etc. at repo root) about 1 hour ago
example.png

1.43 MB
xet

Regenerate example with higher mask alpha about 21 hours ago
infer.py

3.28 kB
Load the model config from the single root config.yaml instead of weights/model.yaml 34 minutes ago
requirements.txt

86 Bytes
Initial release: LUNetv2 SwinV2-Large retinal AV segmentation, RLAD-augmented about 21 hours ago
table3_dataset_ablation.png

108 kB
xet

Add Table 3 (dataset ablation) about 21 hours ago
table4_pretraining.png

123 kB
xet

Add Table 4 (pretraining/generation ablation) about 21 hours ago