Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+exdark_rfdetr-medium_showcase.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,292 @@
+---
+license: apache-2.0
+
+pipeline_tag: object-detection
+
+library_name: rfdetr
+
+datasets:
+  - dronefreak/ExDark
+
+tags:
+  - object-detection
+  - detectionbench
+  - rfdetr
+  - pytorch
+  - computer-vision
+  - low-light
+  - night-images
+  - dark-images
+  - robustness
+metrics:
+  - map50
+  - map50-95
+  - precision
+  - recall
+  - f1
+
+base_model: "rf-detr-medium.pth"
+---
+
+
+# RF-DETR Medium Finetuned on ExDark
+
+Fine-tuned RF-DETR Medium object detector on the **ExDark** benchmark dataset, trained and evaluated as part of [DetectionBench](https://github.com/dronefreak/DetectionBench) -- a framework for reproducibly benchmarking modern object detectors with identical training recipes and evaluation metrics across multiple real-world datasets.
+
+<br>
+
+<!-- ROW 1: Identity & Tech Stack -->
+<div style="display: flex; justify-content: center; align-items: center; gap: 8px; margin-bottom: 8px; flex-wrap: wrap;">
+  <img src="https://img.shields.io/badge/Task-Object_Detection-blue?style=flat-square" alt="Task">
+  <img src="https://img.shields.io/badge/Framework-RF--DETR-0aa1a7?style=flat-square" alt="Framework">
+  <img src="https://img.shields.io/badge/Base_Model-RF--DETR_Medium-purple?style=flat-square" alt="Base Model">
+</div>
+
+<!-- ROW 2: Performance Metrics -->
+<div style="display: flex; justify-content: center; align-items: center; gap: 8px; margin-bottom: 8px; flex-wrap: wrap;">
+  <img src="https://img.shields.io/badge/mAP@50-88.64%25-success?style=flat-square" alt="mAP@50">
+  <img src="https://img.shields.io/badge/mAP@50:95-62.55%25-orange?style=flat-square" alt="mAP@50:95">
+  <img src="https://img.shields.io/badge/Params-33.7M-lightgrey?style=flat-square" alt="Params">
+</div>
+
+<!-- ROW 3: Metadata -->
+<div style="display: flex; justify-content: center; align-items: center; gap: 8px; margin-bottom: 24px; flex-wrap: wrap;">
+  <img src="https://img.shields.io/badge/License-Apache--2.0-lightgrey?style=flat-square" alt="License">
+  <a href="https://github.com/dronefreak/DetectionBench"><img src="https://img.shields.io/badge/Source-DetectionBench-black?style=flat-square" alt="Source"></a>
+</div>
+
+---
+
+## Detection Showcase
+
+<p align="center">
+  <img src="exdark_rfdetr-medium_showcase.jpg" alt="ExDark Detection Demo" width="900">
+</p>
+
+---
+
+## Performance
+
+| Metric     | Score (%)       |
+| ---------- | --------------- |
+| mAP@50     | 88.64     |
+| mAP@50-95  | 62.55   |
+| Precision  | 86.6 |
+| Recall     | 79.46    |
+| F1 Score   | 82.88        |
+| Parameters | 33.7M    |
+| FLOPs      | N/A (not published upstream)     |
+
+---
+
+## Evaluation Protocol
+
+Metrics reported in this model card are computed on the ExDark **test** split, using DetectionBench's standard evaluation pipeline (`detectionbench-evaluate`).
+
+---
+
+## ExDark Model Zoo
+
+Every model DetectionBench has trained and evaluated on ExDark so far, for full transparency -- see [DetectionBench](https://github.com/dronefreak/DetectionBench) for the smaller, curated comparison set used on the project README.
+
+| Rank                       | Model                | mAP@50        | mAP@50-95       | Precision         | Recall         |
+| -------------------------- | --------------------- | ------------- | --------------- | ----------------- | -------------- |
+| 1           | RF-DETR Small | 88.98 | 61.67 | 83.07 | 81.89 |
+| 2           | RF-DETR Medium | 88.64 | 62.55 | 86.6 | 79.46 |
+| 3           | RF-DETR Nano | 85.27 | 58.01 | 85.18 | 74.67 |
+| 4           | YOLOv26l | 77.51 | 50.88 | 80.71 | 70.72 |
+| 5           | YOLOv26m | 76.54 | 50.02 | 82.29 | 68.83 |
+| 6           | YOLOv8x | 75.4 | 48.39 | 81.53 | 65.86 |
+| 7           | YOLOv8l | 75.26 | 48.48 | 81.44 | 67.58 |
+| 8           | YOLOv8m | 74.69 | 48.05 | 78.4 | 69.17 |
+| 9           | YOLOv11x | 74.41 | 48.98 | 81.87 | 67.05 |
+| 10           | YOLOv9m | 74.17 | 47.38 | 76.27 | 67.94 |
+| 11           | YOLOv26s | 74.0 | 48.32 | 79.11 | 65.59 |
+| 12           | YOLOv11l | 73.44 | 47.56 | 78.57 | 67.09 |
+| 13           | YOLOv11s | 73.35 | 46.8 | 77.93 | 66.38 |
+| 14           | YOLOv11m | 73.17 | 47.16 | 74.83 | 67.23 |
+| 15           | YOLOv8s | 73.01 | 45.85 | 78.26 | 65.13 |
+| 16           | YOLOv26n | 72.7 | 46.27 | 81.0 | 62.67 |
+| 17           | YOLOv8n | 71.29 | 44.78 | 78.25 | 62.76 |
+| 18           | YOLOv11n | 70.36 | 44.72 | 76.18 | 61.15 |
+---
+
+## Per-Class Performance
+
+| Class                      | mAP@50          | mAP@50-95         |
+| -------------------------- | --------------- | ----------------- |
+| Bicycle       | 84.51 | 58.56 |
+| Boat       | 89.93 | 55.03 |
+| Bottle       | 81.39 | 54.66 |
+| Bus       | 92.25 | 75.09 |
+| Car       | 91.94 | 66.21 |
+| Cat       | 91.27 | 66.74 |
+| Chair       | 84.52 | 60.12 |
+| Cup       | 88.85 | 60.17 |
+| Dog       | 91.77 | 70.9 |
+| Motorbike       | 91.55 | 64.08 |
+| People       | 89.01 | 56.93 |
+| Table       | 86.74 | 62.17 |
+---
+
+## Evaluation Visualizations
+
+This model was evaluated with [Supervision](https://github.com/roboflow/supervision)'s detection metrics, which report mAP/Precision/Recall directly but don't produce PR-curve, F1-curve, or confusion-matrix plot images the way Ultralytics' validator does. See the Performance table above for Precision/Recall/F1 and the per-class table above for the full per-class mAP breakdown.
+
+---
+
+## Dataset
+
+This model was trained on **ExDark**. For the full dataset description, provenance, license, and citation, see the dataset card:
+
+https://huggingface.co/datasets/dronefreak/ExDark
+
+### Classes
+
+* Bicycle
+* Boat
+* Bottle
+* Bus
+* Car
+* Cat
+* Chair
+* Cup
+* Dog
+* Motorbike
+* People
+* Table
+---
+
+## Usage
+
+### Install Dependencies
+
+```bash
+pip install rfdetr huggingface_hub
+```
+
+### Load Model from Hugging Face
+
+```python
+from huggingface_hub import hf_hub_download
+import rfdetr
+
+weights = hf_hub_download(
+    repo_id="dronefreak/exdark-rfdetr-medium",
+    filename="checkpoint_best_total.pth"
+)
+
+model = rfdetr.RFDETRMedium(pretrain_weights=weights)
+```
+
+### Run Inference
+
+```python
+detections = model.predict("image.jpg", threshold=0.25)
+```
+---
+
+## Training Configuration
+
+| Setting          | Value                           |
+| ---------------- | -------------------------------- |
+| Dataset          | ExDark       |
+| Framework        | RF-DETR                  |
+| Training Toolkit | DetectionBench                   |
+| Epochs (configured max) | 500 |
+| Epochs (actually trained) | 104 |
+| Early Stopping Patience | 100 |
+| Batch Size | 9 |
+| Resolution | 576 |
+| Optimizer | adamw |
+| Learning Rate | 0.0001 |
+| Seed | 42 |
+---
+
+## Repository Contents
+
+```text
+checkpoint_best_total.pth
+metrics.csv
+config.json
+exdark_rfdetr-medium_showcase.jpg
+README.md
+```
+
+---
+
+## Related Resources
+
+* [ExDark dataset card](https://huggingface.co/datasets/dronefreak/ExDark) on Hugging Face
+* [DetectionBench](https://github.com/dronefreak/DetectionBench) -- reproducible benchmarks for modern object detectors on real-world datasets
+
+---
+
+## Training Framework
+
+This model was trained using [DetectionBench](https://github.com/dronefreak/DetectionBench), an open-source framework for benchmarking object detectors across multiple real-world datasets with a common pipeline.
+
+Features include:
+
+* A dataset-adapter registry for converting real-world datasets into a canonical format
+* Identical training/evaluation recipes across model families (Ultralytics YOLO/RT-DETR, RF-DETR)
+* Hardware profiling (latency, FPS, VRAM, parameters, FLOPs)
+* One-command reproducibility via versioned Hydra configs
+
+If you find this model useful, please consider starring the repository.
+
+---
+
+## Known Limitations
+
+* Severe class imbalance: `People` accounts for roughly 46% of all annotated boxes while `Bus` is the rarest class, so per-class accuracy on rare classes is measured on very few test examples and should be read with wide uncertainty.
+* Small dataset overall (7,344 images, 734 in the test split, across 12 classes) -- limited training signal for several classes independent of the imbalance above.
+* Two-hop provenance: this dataset was converted to YOLO format by a third-party Roboflow export before reaching DetectionBench, not sourced directly from the original per-class-folder release; images are pre-resized to 640x640 by that export.
+* The original authors separately request non-commercial use of this dataset (beyond the BSD-3-Clause license text itself) -- this applies to any model trained on it, not only the raw images.
+---
+
+## Citation
+
+If you use this model in your research, please consider citing:
+
+1. The ExDark dataset (see below)
+2. The original RF-DETR Medium architecture (see below)
+3. DetectionBench, the training/evaluation framework used to produce this checkpoint
+
+```
+@article{Exdark,
+  title = {Getting to Know Low-light Images with The Exclusively Dark Dataset},
+  author = {Loh, Yuen Peng and Chan, Chee Seng},
+  journal = {Computer Vision and Image Understanding},
+  volume = {178},
+  pages = {30-42},
+  year = {2019},
+  doi = {https://doi.org/10.1016/j.cviu.2018.10.010}
+}
+```
+
+```bibtex
+@inproceedings{robinson2026rfdetr,
+  title     = {RF-DETR: Real-Time Detection Transformer},
+  author    = {Robinson, Isaac and Robicheaux, Peter and Popov, Matvei and Ramanan, Deva and Peri, Neehar},
+  booktitle = {International Conference on Learning Representations (ICLR)},
+  year      = {2026},
+  url       = {https://arxiv.org/abs/2511.09554}
+}
+
+@article{oquab2023dinov2,
+  title={DINOv2: Learning Robust Visual Features without Supervision},
+  author={Oquab, Maxime and Darcet, Timoth{\'e}e and Moutakanni, Theo and Vo, Huy and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and others},
+  journal={arXiv preprint arXiv:2304.07193},
+  year={2023}
+}
+```
+
+```bibtex
+@software{Saksena_DetectionBench_2026,
+  author = {Saksena, Saumya Kumaar},
+  title = {DetectionBench: Reproducible Benchmarks for Modern Object Detectors on Real-World Datasets},
+  url = {https://github.com/dronefreak/DetectionBench},
+  year = {2026}
+}
+```

checkpoint_best_total.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5909b9f6daea71b90f0c22d9f15b436bdf7242e2d0c146ccf1907b0c4ce6ea78
+size 133838227

config.json

@@ -0,0 +1,157 @@
+{
+  "train_config": {
+    "lr": 0.0001,
+    "lr_encoder": 0.00015,
+    "batch_size": 9,
+    "grad_accum_steps": 2,
+    "auto_batch_target_effective": 16,
+    "auto_batch_max_targets_per_image": 100,
+    "auto_batch_ema_headroom": 0.7,
+    "epochs": 500,
+    "resume": null,
+    "ema_decay": 0.993,
+    "ema_tau": 100,
+    "lr_drop": 100,
+    "checkpoint_interval": 100,
+    "skip_best_epochs": 0,
+    "smooth_alpha": 0.0,
+    "warmup_epochs": 0.0,
+    "lr_vit_layer_decay": 0.8,
+    "lr_component_decay": 0.7,
+    "drop_path": 0.0,
+    "cls_loss_coef": 1.0,
+    "keypoint_flip_pairs": [],
+    "keypoint_l1_loss_coef": 0,
+    "keypoint_findable_loss_coef": 0,
+    "keypoint_visible_loss_coef": 0,
+    "keypoint_nll_loss_coef": 0,
+    "keypoint_oks_sigmas": null,
+    "dataset_file": "roboflow",
+    "square_resize_div_64": true,
+    "dataset_dir": "/home/saumya.saksena/projects/ExDark/data",
+    "output_dir": "/home/saumya.saksena/projects/DetectionBench/experiments/exdark/rfdetr-medium",
+    "multi_scale": true,
+    "expanded_scales": true,
+    "do_random_resize_via_padding": false,
+    "use_ema": true,
+    "ema_update_interval": 1,
+    "eval_ema_only": false,
+    "num_workers": 4,
+    "weight_decay": 0.0001,
+    "amp_dtype": "auto",
+    "early_stopping": true,
+    "early_stopping_patience": 100,
+    "early_stopping_min_delta": 0.001,
+    "early_stopping_use_ema": false,
+    "progress_bar": "rich",
+    "tensorboard": true,
+    "wandb": false,
+    "mlflow": false,
+    "clearml": false,
+    "project": null,
+    "run": null,
+    "class_names": null,
+    "run_test": false,
+    "eval_max_dets": 500,
+    "eval_interval": 1,
+    "log_per_class_metrics": true,
+    "eval_masks_head_resolution": false,
+    "aug_config": null,
+    "scale_jitter": true,
+    "augmentation_backend": "kornia",
+    "save_dataset_grids": false,
+    "notes": null,
+    "accelerator": "auto",
+    "clip_max_norm": 0.1,
+    "seed": 42,
+    "sync_bn": false,
+    "strategy": "auto",
+    "devices": 1,
+    "num_nodes": 1,
+    "fp16_eval": false,
+    "lr_scheduler": "step",
+    "lr_scheduler_kwargs": {},
+    "lr_scheduler_interval": "step",
+    "lr_scheduler_monitor": "val/loss",
+    "lr_min_factor": 0.0,
+    "optimizer": "adamw",
+    "optimizer_kwargs": {},
+    "dont_save_weights": false,
+    "train_log_sync_dist": false,
+    "train_log_on_step": false,
+    "compute_train_metrics": false,
+    "compute_val_loss": true,
+    "compute_test_loss": true,
+    "pin_memory": null,
+    "persistent_workers": null,
+    "prefetch_factor": null
+  },
+  "model_config": {
+    "encoder": "dinov2_windowed_small",
+    "out_feature_indexes": [
+      3,
+      6,
+      9,
+      12
+    ],
+    "dec_layers": 4,
+    "two_stage": true,
+    "projector_scale": [
+      "P4"
+    ],
+    "hidden_dim": 256,
+    "patch_size": 16,
+    "num_windows": 2,
+    "sa_nheads": 8,
+    "ca_nheads": 16,
+    "dec_n_points": 2,
+    "num_queries": 300,
+    "num_select": 300,
+    "postprocess_trace_alpha": 0.2,
+    "bbox_reparam": true,
+    "lite_refpoint_refine": true,
+    "layer_norm": true,
+    "amp": true,
+    "num_channels": 3,
+    "num_classes": 12,
+    "pretrain_weights": "/home/saumya.saksena/.roboflow/models/rf-detr-medium.pth",
+    "device": "cuda",
+    "resolution": 576,
+    "group_detr": 13,
+    "gradient_checkpointing": false,
+    "compile": false,
+    "fused_optimizer": true,
+    "positional_encoding_size": 36,
+    "ia_bce_loss": true,
+    "segmentation_head": false,
+    "use_grouppose_keypoints": false,
+    "keypoint_cross_attn": true,
+    "inter_instance_kp_attn": false,
+    "grouppose_keypoint_dim_downscale": 1,
+    "dual_projector": false,
+    "dual_projector_kp_only": false,
+    "num_keypoints_per_class": [],
+    "num_decoder_registers": 0,
+    "mask_downsample_ratio": 4,
+    "backbone_lora": false,
+    "freeze_encoder": false,
+    "license": "Apache-2.0",
+    "model_name": "RFDETRMedium"
+  },
+  "model_config_type": "RFDETRMediumConfig",
+  "class_names": [
+    "Bicycle",
+    "Boat",
+    "Bottle",
+    "Bus",
+    "Car",
+    "Cat",
+    "Chair",
+    "Cup",
+    "Dog",
+    "Motorbike",
+    "People",
+    "Table"
+  ],
+  "num_classes": 12
+}