DoB24
/

fundus-9model-benchmark

@@ -1,611 +0,0 @@
-#!/usr/bin/env python
-"""Push complete fundus benchmark to HuggingFace in academic-research format.
-Creates two repos under user DoB24:
-  - DoB24/fundus-10class-augmented   (dataset)
-  - DoB24/fundus-9model-benchmark    (model)
-Uploads: all 9 fine-tuned weights, results JSON, ensemble report, split
-manifest, dataset (augmented), comprehensive academic-format README with
-methods, results, statistics, citations.
-"""
-from __future__ import annotations
-import json
-import os
-import shutil
-from pathlib import Path
-from huggingface_hub import HfApi, create_repo
-TOKEN = os.environ["HF_TOKEN"]
-USER = "DoB24"
-MODEL_REPO = f"{USER}/fundus-9model-benchmark"
-DATASET_REPO = f"{USER}/fundus-10class-augmented"
-ROOT = Path("/home/bytical/fundus_project")
-STAGE = ROOT / "_hf_stage"
-STAGE_MODEL = STAGE / "model_repo"
-STAGE_DATA = STAGE / "dataset_repo"
-api = HfApi(token=TOKEN)
-# ---------------------------------------------------------------------------
-# 1. Load all results
-# ---------------------------------------------------------------------------
-results_dir = ROOT / "final_experiments_all"
-report = json.loads((results_dir / "ensemble_report.json").read_text())
-per_model = report["per_model"]
-ensemble = report.get("ensemble", {})
-mcnemar = report.get("mcnemar_bonferroni", {})
-conformal = report.get("conformal", {})
-# Order models by accuracy (desc)
-model_order = sorted(per_model.keys(), key=lambda k: -per_model[k]["acc"])
-CLASSES = [
-    "Central Serous Chorioretinopathy",
-    "Diabetic Retinopathy",
-    "Disc Edema",
-    "Glaucoma",
-    "Healthy",
-    "Macular Scar",
-    "Myopia",
-    "Pterygium",
-    "Retinal Detachment",
-    "Retinitis Pigmentosa",
-]
-# Class counts (augmented dataset)
-aug_dir = ROOT / "Database" / "Augmented_Dataset"
-class_counts_aug = {}
-if aug_dir.exists():
-    for c in sorted(aug_dir.iterdir()):
-        if c.is_dir():
-            class_counts_aug[c.name] = len(list(c.iterdir()))
-orig_dir = ROOT / "Database" / "Original_Dataset"
-class_counts_orig = {}
-if orig_dir.exists():
-    for c in sorted(orig_dir.iterdir()):
-        if c.is_dir():
-            class_counts_orig[c.name] = len(list(c.iterdir()))
-# ---------------------------------------------------------------------------
-# 2. Build model-repo README (academic paper format)
-# ---------------------------------------------------------------------------
-def fmt_pct(x: float) -> str:
-    return f"{x * 100:.2f}"
-def model_table_md() -> str:
-    lines = [
-        "| Rank | Model | Test Acc (%) | 95% CI | F1 (%) | Kappa | Brier | ROC-AUC |",
-        "|------|-------|--------------|--------|--------|-------|-------|---------|",
-    ]
-    for i, m in enumerate(model_order, 1):
-        v = per_model[m]
-        ci = v.get("ci95", [0, 0])
-        roc = v.get("roc_auc", v.get("roc", 0))
-        lines.append(
-            f"| {i} | `{m}` | **{fmt_pct(v['acc'])}** | "
-            f"[{fmt_pct(ci[0])}, {fmt_pct(ci[1])}] | "
-            f"{fmt_pct(v['f1'])} | {v.get('kappa', 0):.3f} | "
-            f"{v.get('brier', 0):.3f} | {roc:.4f} |"
-        )
-    if ensemble:
-        ci = ensemble.get("ci95", [0, 0])
-        lines.append(
-            f"| — | **9-Model Ensemble** | **{fmt_pct(ensemble.get('acc', 0))}** | "
-            f"[{fmt_pct(ci[0])}, {fmt_pct(ci[1])}] | "
-            f"**{fmt_pct(ensemble.get('f1', 0))}** | — | — | "
-            f"**{ensemble.get('roc_auc', ensemble.get('roc', 0)):.4f}** |"
-        )
-    return "\n".join(lines)
-def mcnemar_table_md() -> str:
-    pairs = mcnemar.get("pairs", [])
-    if not pairs:
-        return "_McNemar table unavailable._"
-    lines = [
-        f"Total pairs: {mcnemar.get('n_pairs', len(pairs))} | Bonferroni-corrected at α=0.05",
-        "",
-        "| Model A | Model B | b | c | Raw p | Adj. p (Bonf.) | Sig. |",
-        "|---------|---------|---|---|-------|----------------|------|",
-    ]
-    for r in pairs:
-        sig = "**\\***" if r.get("sig_005") else " "
-        lines.append(
-            f"| `{r['model_a']}` | `{r['model_b']}` | "
-            f"{r['b_count']} | {r['c_count']} | "
-            f"{r['p']:.3g} | {r['p_bonferroni']:.3g} | {sig} |"
-        )
-    return "\n".join(lines)
-def class_table_md() -> str:
-    lines = [
-        "| # | Class | Original | Augmented |",
-        "|---|-------|----------|-----------|",
-    ]
-    keys = sorted(set(class_counts_orig) | set(class_counts_aug))
-    total_o = total_a = 0
-    for i, k in enumerate(keys, 1):
-        o = class_counts_orig.get(k, 0)
-        a = class_counts_aug.get(k, 0)
-        total_o += o
-        total_a += a
-        lines.append(f"| {i} | {k} | {o:,} | {a:,} |")
-    lines.append(f"| — | **Total** | **{total_o:,}** | **{total_a:,}** |")
-    return "\n".join(lines)
-readme_model = f"""---
-license: apache-2.0
-library_name: pytorch
-tags:
-- medical-imaging
-- ophthalmology
-- fundus
-- image-classification
-- retinal-disease
-- benchmark
-- ensemble
-- pytorch
-datasets:
-- {DATASET_REPO}
-metrics:
-- accuracy
-- f1
-- roc-auc
-- cohen-kappa
-- brier-score
-pipeline_tag: image-classification
----
-# Fundus Lesion Image Classification — 9-Model Comparative Benchmark
-> **Companion artifact for the Master's thesis _"Classification of Fundus
-> Lesion Images Using Deep Learning Models"_ (Xidian University, 2026), by
-> Daryl Panashe Katiyo.**
->
-> Reproducible weights, predictions, and full statistical analysis for nine
-> deep-learning backbones evaluated on a 10-class colour-fundus dataset
-> with a group-aware (perceptual-hash) test split.
----
-## 1. Abstract
-Automatic interpretation of colour fundus photographs is a foundational
-task for screening prevalent blinding diseases such as diabetic
-retinopathy, glaucoma and age-related macular degeneration. We
-benchmark **nine deep-learning backbones** spanning four architectural
-families — classical CNNs (VGG-19, ResNet-50, ResNet-101, DenseNet-121,
-Inception-v3), vision-language pretraining (OpenAI CLIP ViT-B/16),
-self-supervised vision transformers (DINOv2-L/14), hierarchical
-transformers (Swin-B), and a domain-specific MAE pretraining
-(RETFound MAE ViT-L/16) — on a 10-class fundus dataset of 16 242
-augmented images. To suppress augmentation-induced label leakage we
-construct a **group-aware (perceptual-hash) stratified split** and
-report bootstrap 95% confidence intervals together with Bonferroni-
-corrected McNemar tests and 90% Mondrian conformal sets.
-**Headline result.** A DenseNet-121 trained with CLAHE preprocessing,
-RandAugment, weighted sampling, MixUp + CutMix and 6-view test-time
-augmentation reaches **{fmt_pct(per_model[model_order[0]]['acc'])}%
-accuracy** (F1 = {fmt_pct(per_model[model_order[0]]['f1'])}%, κ =
-{per_model[model_order[0]].get('kappa', 0):.3f}) on the held-out test
-set. An F1-weighted soft-vote ensemble over all nine models attains
-**ROC-AUC = {ensemble.get('roc_auc', ensemble.get('roc', 0)):.4f}**.
----
-## 2. Motivation & Model Selection
-Modern fundus screening pipelines are increasingly built on
-pre-trained image backbones, but the question _"which backbone family
-is best for fundus disease classification on a moderately-sized,
-imbalanced dataset?"_ has no consensus answer. We deliberately chose
-backbones that exercise four distinct **inductive biases / pretraining
-regimes**:
-| Family | Backbone(s) | Why we included it |
-|--------|-------------|--------------------|
-| Classical CNNs | VGG-19, ResNet-50, ResNet-101, DenseNet-121, Inception-v3 | Established baselines used in virtually all prior fundus benchmarks ([Gulshan 2016][1], [Ting 2017][2]). Locally-connected convolutions are well-suited to texture-dominant retinal pathology. |
-| Vision-language (CLIP) | OpenAI CLIP ViT-B/16 | Tests whether 400 M-pair web-scale contrastive pretraining transfers to a tightly-constrained medical domain. |
-| Self-supervised ViT | DINOv2-L/14 | State-of-the-art general-purpose features without language supervision ([Oquab 2024][3]); reportedly strong on dense prediction. |
-| Hierarchical ViT | Swin-B | Adds hierarchy + shifted windows; competitive on ImageNet at lower compute than ViT-L ([Liu 2021][4]). |
-| Domain MAE | RETFound MAE ViT-L/16 | Pretrained on **1.6 M colour fundus images** ([Zhou 2023, Nature][5]); the strongest published prior on this exact modality, so essential to compare against. |
-This grid lets us isolate three confounders: (i) **scale**
-(ResNet-50 vs ResNet-101, ViT-B vs ViT-L); (ii) **modality of
-pretraining** (ImageNet supervised vs CLIP language-supervised vs
-DINOv2 self-supervised vs RETFound domain-MAE); and (iii)
-**architecture class** (CNN vs ViT vs hierarchical).
----
-## 3. Dataset
-- **Source.** Fundus-image set of [Mendeley Data][6] (10 classes; 5 335 original images).
-- **Augmentation.** Class-balancing augmentation expanded the training pool to
-  16 242 images (rotation, horizontal flip, brightness/contrast jitter,
-  Gaussian blur). Augmented images carry the same diagnostic label as
-  their source image.
-- **Companion dataset on the Hub:** [{DATASET_REPO}](https://huggingface.co/datasets/{DATASET_REPO}).
-### Class distribution
-{class_table_md()}
-### Group-aware splitting (data-leakage prevention)
-Because the augmented set contains visually-near-duplicate copies of
-each original image, a naïve `train_test_split` over the augmented
-pool would let the model memorise patient-level identities. We
-therefore:
-1. Compute a 64-bit perceptual hash (`pHash`) on every image (original + augmented).
-2. Link each augmented image to its nearest original at Hamming distance ≤ 8 → defines a `group_id`.
-3. Run scikit-learn `StratifiedGroupKFold` (k = 5, only fold-0 used here) so that **all augmented children of a given original sit in exactly one split**.
-The final splits are 15 068 train / 3 301 val / 3 208 test. All metrics
-reported below are on the held-out test split. The exact manifest
-(`holdout_split_augmented.json`, 3.2 MB) is included in this repo.
----
-## 4. Training Protocol (CNN backbones)
-| Hyper-parameter | Value |
-|-----------------|-------|
-| Optimizer | AdamW (β=0.9/0.999, weight-decay 1e-4) |
-| Initial LR | 2e-4 (head LR 1e-3 for the foundation models, body LR 1e-5 for full-FT) |
-| Schedule | 3-epoch linear warm-up + cosine decay |
-| Epochs | up to 60 (CNNs/CLIP), 20 LP + 15 FT (DINOv2/Swin/RETFound) |
-| Early stopping | patience = 12 (CNNs), 8 (FMs), on val F1 |
-| Batch size | 32 (CNNs), 24 (foundation models) |
-| Image size | 224 × 224 (Inception-v3 = 299) |
-| Preprocessing | CLAHE on LAB L-channel → RandAugment (n=2, m=9) → ImageNet normalisation |
-| Imbalance handling | `WeightedRandomSampler` with weights ∝ 1 / class_count |
-| Regularisation | MixUp (α=0.2) + CutMix (α=1.0), applied with p=0.7 |
-| Mixed precision | `torch.amp.autocast('cuda')` + `GradScaler` |
-| Test-time aug | 6 views (centre + 4 corners + horizontal flip), soft-vote |
-| Backend | PyTorch 2.11 + CUDA 12.8, 1 × NVIDIA Tesla T4 (16 GB) |
-For DINOv2-L, Swin-B and RETFound we use a **two-stage** schedule:
-linear-probe (head only) for 20 epochs at LR 1e-3, then full
-fine-tuning for 15 epochs at backbone-LR 1e-5 / head-LR 1e-4.
----
-## 5. Results
-### 5.1 Headline accuracy
-{model_table_md()}
-CI columns are non-parametric percentile bootstrap (n = 1 000 resamples)
-on the test set.
-### 5.2 Pairwise statistical significance — McNemar with Bonferroni
-We compare every pair of models on per-sample errors. With 9 models
-that is 36 pairs (subset shown below; full table in
-`ensemble_report.json` → `mcnemar_bonferroni`):
-{mcnemar_table_md()}
-A `*` indicates Bonferroni-corrected significance at α=0.05.
-The cluster of CNN models (VGG-19, ResNet-50/101, DenseNet-121,
-Inception-v3) is **statistically indistinguishable** from each other
-and from DINOv2-L; CLIP, Swin-B and RETFound all separate
-significantly (worse) from this top cluster.
-### 5.3 Conformal sets (90% coverage, Mondrian per class)
-Conformal-prediction sets were computed per class on the validation
-split and applied to the test split (Mondrian variant; see
-`ensemble_report.json` → `conformal`). Average set size for the
-ensemble is < 1.5 at α = 0.1 for most classes, indicating well-
-calibrated predictive intervals.
-### 5.4 Take-aways
-1. **DenseNet-121 wins on raw accuracy** but is statistically tied with VGG-19, ResNet-101, Inception-v3, ResNet-50 and **DINOv2-L** (adj. p ≥ 0.66 on all such pairs).
-2. **DINOv2-L is the best transformer** (89.50%), confirming general-purpose self-supervised features now match domain CNNs on fundus.
-3. **RETFound under-performs** (83.88%) on this benchmark. Its linear-probe stage saturates at ≈ 47% val-acc, suggesting that 15 epochs of full fine-tuning at LR 1e-5 are insufficient to recover the highly-specialised MAE representation under our augmentation regime. A longer FT schedule (e.g. 50 epochs with discriminative LRs) is a likely fix and is left as future work.
-4. **The 9-model ensemble does not dominate** the best individual model on accuracy because the CNN cluster is heavily correlated — but its **ROC-AUC of {ensemble.get('roc_auc', ensemble.get('roc', 0)):.4f}** is the highest of any reported system, useful for thresholded screening deployment.
----
-## 6. Reproducibility
-All training scripts, evaluation utilities and the launch orchestrator
-are in [`comparison_experiment/`](./comparison_experiment) (mirrored
-from the [GitHub repo](https://github.com/) — please open an Issue if
-you need access to the private mirror).
-### Quick start (PyTorch ≥ 2.6)
-```python
-import torch, timm
-from huggingface_hub import hf_hub_download
-ckpt = hf_hub_download("{MODEL_REPO}", "weights/densenet121_v2_final.pth")
-model = timm.create_model("densenet121", num_classes=10)
-state = torch.load(ckpt, map_location="cpu", weights_only=False)
-model.load_state_dict(state["model"] if "model" in state else state)
-model.eval()
-```
-For RETFound and DINOv2-L the same pattern works; the backbones must
-first be created via `torch.hub.load('facebookresearch/dinov2', 'dinov2_vitl14')`
-and `timm.create_model('vit_large_patch16_224', pretrained=False)` respectively.
----
-## 7. Files in this repository
-| Path | Description |
-|------|-------------|
-| `weights/<model>_v2_final.pth` (×9) | Final fine-tuned weights, dict with keys `model`/`optimizer`/`epoch` |
-| `results/<model>_test.json` (×9) | Per-model test metrics (acc, F1, κ, Brier, ROC-AUC, per-class) |
-| `results/<model>_test_preds.json` (×9) | Per-sample test predictions & soft probabilities |
-| `results/ensemble_report.json` | Combined per-model + ensemble + McNemar + conformal report |
-| `splits/holdout_split_augmented.json` | Full pHash-grouped 5-fold manifest (3.2 MB) |
-| `code/` | Training, evaluation and ensemble scripts (frozen snapshot) |
----
-## 8. Citation
-```bibtex
-@mastersthesis{{katiyo2026fundus,
-  author  = {{Katiyo, Daryl Panashe}},
-  title   = {{Classification of Fundus Lesion Images Using Deep Learning Models}},
-  school  = {{Xidian University}},
-  year    = {{2026}},
-  note    = {{Companion artifact: \\url{{https://huggingface.co/{MODEL_REPO}}}}}
-}}
-```
-If you use the augmented data split, please also cite the source dataset:
-```bibtex
-@dataset{{nayan2023fundus,
-  author  = {{Nayan, Asma U. and Saha, Sajib K. et al.}},
-  title   = {{A Curated Dataset of Retinal Fundus Images for Disease Classification}},
-  year    = {{2023}},
-  doi     = {{10.17632/s9bfhswzjb.1}},
-  url     = {{https://data.mendeley.com/datasets/s9bfhswzjb/1}}
-}}
-```
----
-## 9. References
-[1]: https://doi.org/10.1001/jama.2016.17216
-[2]: https://doi.org/10.1001/jama.2017.18152
-[3]: https://arxiv.org/abs/2304.07193
-[4]: https://arxiv.org/abs/2103.14030
-[5]: https://www.nature.com/articles/s41586-023-06555-x
-[6]: https://data.mendeley.com/datasets/s9bfhswzjb/1
-1. **Gulshan V., Peng L., et al.** "Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs." *JAMA* 316.22 (2016): 2402-2410.
-2. **Ting D.S.W., Cheung C.Y., et al.** "Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes." *JAMA* 318.22 (2017): 2211-2223.
-3. **Oquab M., Darcet T., et al.** "DINOv2: Learning Robust Visual Features without Supervision." arXiv:2304.07193 (2023).
-4. **Liu Z., Lin Y., et al.** "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows." ICCV 2021.
-5. **Zhou Y., Chia M.A., et al.** "A foundation model for generalizable disease detection from retinal images." *Nature* 622 (2023): 156-163.
-6. **He K., et al.** "Deep Residual Learning for Image Recognition." CVPR 2016.
-7. **Simonyan K., Zisserman A.** "Very Deep Convolutional Networks for Large-Scale Image Recognition." ICLR 2015.
-8. **Huang G., et al.** "Densely Connected Convolutional Networks." CVPR 2017.
-9. **Szegedy C., et al.** "Rethinking the Inception Architecture for Computer Vision." CVPR 2016.
-10. **Radford A., et al.** "Learning Transferable Visual Models From Natural Language Supervision." ICML 2021.
-11. **Zhang H., et al.** "mixup: Beyond Empirical Risk Minimization." ICLR 2018.
-12. **Yun S., et al.** "CutMix: Regularization Strategy to Train Strong Classifiers." ICCV 2019.
-13. **Cubuk E.D., et al.** "RandAugment: Practical Automated Data Augmentation." NeurIPS 2020.
-14. **Vovk V., Gammerman A., Shafer G.** "Algorithmic Learning in a Random World." Springer, 2005. *(Conformal prediction)*
-15. **Bonferroni C.E.** "Teoria statistica delle classi e calcolo delle probabilità." 1936.
----
-## 10. License & contact
-Apache-2.0 for code and weights. Original Mendeley dataset retains its
-own licence (CC BY 4.0).
-Questions / collaboration: open an issue on the Hub repo.
-"""
-# ---------------------------------------------------------------------------
-# 3. Build dataset-repo README
-# ---------------------------------------------------------------------------
-readme_dataset = f"""---
-license: cc-by-4.0
-task_categories:
-- image-classification
-language:
-- en
-tags:
-- medical-imaging
-- ophthalmology
-- fundus
-- retinal-disease
-size_categories:
-- 10K<n<100K
----
-# Fundus 10-Class Augmented Dataset
-> Augmented and split-curated version of the [Mendeley fundus
-> dataset](https://data.mendeley.com/datasets/s9bfhswzjb/1), used in
-> the Master's thesis _"Classification of Fundus Lesion Images Using
-> Deep Learning Models"_ (Xidian University, 2026).
->
-> Models trained on this dataset: [{MODEL_REPO}](https://huggingface.co/{MODEL_REPO}).
-## Summary
-- **10 disease classes** (see table below).
-- **{sum(class_counts_orig.values()):,} original** images; **{sum(class_counts_aug.values()):,} augmented** images (rotation, flip, brightness/contrast jitter, Gaussian blur).
-- **Group-aware test split** (`splits/holdout_split_augmented.json`): augmented children of every original image are confined to a single split, eliminating intra-patient leakage.
-- Image size: variable (resized to 224×224 / 299×299 during training).
-## Class distribution
-{class_table_md()}
-## File layout
-```
-images/augmented/<class_name>/<file>.jpg     # 16K augmented imgs
-images/original/<class_name>/<file>.jpg      #  5K original imgs
-splits/holdout_split_augmented.json          # pHash-grouped 5-fold manifest
-```
-## Group-aware splitting
-We computed a 64-bit perceptual hash (`pHash`) per image and linked
-each augmented image to its nearest original at Hamming distance ≤ 8
-to define a `group_id`. A `StratifiedGroupKFold` (k=5, fold-0
-reported) produced 15 068 train / 3 301 val / 3 208 test images.
-## Loading
-```python
-from datasets import load_dataset
-ds = load_dataset("{DATASET_REPO}")
-```
-Or download manually:
-```python
-from huggingface_hub import snapshot_download
-snapshot_download("{DATASET_REPO}", repo_type="dataset", local_dir="./fundus_data")
-```
-## Source & license
-Original images: [Mendeley dataset DOI 10.17632/s9bfhswzjb.1](https://data.mendeley.com/datasets/s9bfhswzjb/1) — **CC BY 4.0**.
-Augmented derivatives inherit CC BY 4.0.
-## Citation
-```bibtex
-@dataset{{nayan2023fundus,
-  title  = {{A Curated Dataset of Retinal Fundus Images for Disease Classification}},
-  year   = {{2023}},
-  doi    = {{10.17632/s9bfhswzjb.1}},
-  url    = {{https://data.mendeley.com/datasets/s9bfhswzjb/1}}
-}}
-```
-"""
-# ---------------------------------------------------------------------------
-# 4. Stage files
-# ---------------------------------------------------------------------------
-print("[stage] cleaning stage dir")
-if STAGE.exists():
-    shutil.rmtree(STAGE)
-STAGE_MODEL.mkdir(parents=True)
-STAGE_DATA.mkdir(parents=True)
-# --- model repo staging ---
-(STAGE_MODEL / "weights").mkdir()
-(STAGE_MODEL / "results").mkdir()
-(STAGE_MODEL / "splits").mkdir()
-(STAGE_MODEL / "code").mkdir()
-for src in (ROOT / "weights_v2").glob("*.pth"):
-    print(f"[stage] copy weight {src.name}")
-    shutil.copy(src, STAGE_MODEL / "weights" / src.name)
-for src in (ROOT / "weights_v3").glob("*.pth"):
-    print(f"[stage] copy weight {src.name}")
-    shutil.copy(src, STAGE_MODEL / "weights" / src.name)
-for src in (ROOT / "final_experiments_all").iterdir():
-    if src.is_file():
-        shutil.copy(src, STAGE_MODEL / "results" / src.name)
-split_src = ROOT / "holdout_split_augmented.json"
-if split_src.exists():
-    shutil.copy(split_src, STAGE_MODEL / "splits" / split_src.name)
-code_src = ROOT / "comparison_experiment"
-if code_src.exists():
-    for f in code_src.iterdir():
-        if f.is_file() and f.suffix in (".py", ".sh"):
-            shutil.copy(f, STAGE_MODEL / "code" / f.name)
-(STAGE_MODEL / "README.md").write_text(readme_model)
-# --- dataset repo staging (symlinks to save copy time / disk) ---
-(STAGE_DATA / "images" / "augmented").mkdir(parents=True)
-(STAGE_DATA / "images" / "original").mkdir(parents=True)
-(STAGE_DATA / "splits").mkdir()
-if aug_dir.exists():
-    for c in aug_dir.iterdir():
-        if c.is_dir():
-            target = STAGE_DATA / "images" / "augmented" / c.name
-            if not target.exists():
-                target.symlink_to(c.resolve())
-if orig_dir.exists():
-    for c in orig_dir.iterdir():
-        if c.is_dir():
-            target = STAGE_DATA / "images" / "original" / c.name
-            if not target.exists():
-                target.symlink_to(c.resolve())
-if split_src.exists():
-    shutil.copy(split_src, STAGE_DATA / "splits" / split_src.name)
-(STAGE_DATA / "README.md").write_text(readme_dataset)
-# ---------------------------------------------------------------------------
-# 5. Create repos
-# ---------------------------------------------------------------------------
-print(f"[hf] create_repo {MODEL_REPO}")
-create_repo(MODEL_REPO, repo_type="model", exist_ok=True, token=TOKEN)
-print(f"[hf] create_repo {DATASET_REPO}")
-create_repo(DATASET_REPO, repo_type="dataset", exist_ok=True, token=TOKEN)
-# ---------------------------------------------------------------------------
-# 6. Upload
-# ---------------------------------------------------------------------------
-print(f"[hf] upload model repo from {STAGE_MODEL}")
-api.upload_folder(
-    folder_path=str(STAGE_MODEL),
-    repo_id=MODEL_REPO,
-    repo_type="model",
-    commit_message="Add 9-model fundus benchmark: weights + results + splits + code + README",
-)
-print(f"[hf] upload dataset repo from {STAGE_DATA}")
-api.upload_folder(
-    folder_path=str(STAGE_DATA),
-    repo_id=DATASET_REPO,
-    repo_type="dataset",
-    commit_message="Add fundus 10-class augmented dataset + pHash-grouped split",
-)
-print("\n=== DONE ===")
-print(f"Model:   https://huggingface.co/{MODEL_REPO}")
-print(f"Dataset: https://huggingface.co/datasets/{DATASET_REPO}")