Add on-device learning and optimizer resume: fireviewer_rfdetr_medium_v110

models/fireviewer_rfdetr_medium_v110_learning/CHECKPOINT_LICENSE.md

@@ -0,0 +1,81 @@
+# FireViewer Model Use License v1.0
+
+Copyright © FireViewer contributors / applicable rights holders.
+
+These terms apply to the **FireViewer-trained checkpoint and FireViewer-published conversions or derived deployment artifacts** identified by the repository that includes this file.
+
+They do not replace third-party licences that apply to upstream software, architectures, base models or other third-party components. FireViewer grants rights only to the extent it is entitled to grant them.
+
+## 1. Permitted uses
+
+Subject to these terms, you may:
+
+1. use the Model for research, testing and evaluation;
+2. perform internal evaluation for a potential commercial product or service;
+3. use the Model commercially **without redistributing the Model**, provided that the required FireViewer attribution is preserved;
+4. internally convert, optimize or quantize the Model, including to formats such as ONNX, TensorRT, LiteRT/TFLite, FP16, INT8, NVFP4 or another technically applicable format;
+5. internally fine-tune the Model.
+
+## 2. Attribution for free commercial use
+
+Commercial use under these free terms requires a reasonable public FireViewer credit where product or service credits, acknowledgements, legal notices or technical documentation are normally presented.
+
+Recommended attribution:
+
+> Fire/smoke detection model by FireViewer — https://huggingface.co/fireviewer
+
+Where practical, link directly to the specific FireViewer model repository.
+
+A separate written commercial agreement may waive the **public FireViewer attribution** requirement.
+
+Upstream notices that independently apply to third-party components remain required and are not waived by FireViewer.
+
+## 3. Redistribution is not granted
+
+You may **not** redistribute the Model.
+
+Redistribution includes providing, transferring, sublicensing, publishing, mirroring, selling, leasing, embedding or otherwise making available to a third party:
+
+- the original FireViewer checkpoint;
+- a converted or quantized version;
+- a fine-tuned version;
+- a pruned, merged or otherwise weight-derived version;
+- an official FireViewer deployment artifact obtained from the repository.
+
+Embedding the Model in hardware, software, firmware, an appliance, an edge device, NAS, NVR, camera system or other on-premise product that is **delivered to a third party** is redistribution under these terms.
+
+A hosted service in which the Model remains under the operator's control and customers only receive outputs is not, by itself, redistribution of the Model.
+
+## 4. Derived and converted weights
+
+Internal conversions, quantization and fine-tuning are permitted, but the resulting weights remain subject to the non-redistribution condition above.
+
+These terms do not claim rights over independently created software that merely calls or interoperates with the Model, except to the extent that distribution of that software also distributes Model weights.
+
+## 5. Official additional formats
+
+FireViewer may publish additional official deployment formats on request. Publishing an official FireViewer conversion does not grant redistribution rights beyond these terms. Third parties may not present an unofficial conversion as an official FireViewer artifact.
+
+## 6. Separate commercial agreement
+
+A separate written agreement may provide different terms, including commercial use without public FireViewer attribution.
+
+Unless that written agreement expressly says otherwise, it does **not** grant redistribution or sublicensing rights.
+
+## 7. No transfer of trademarks
+
+These terms do not grant a right to use FireViewer names, logos or marks except for factual attribution and identification of the Model.
+
+## 8. No warranty
+
+The Model is provided "AS IS", without warranties or conditions of any kind, to the maximum extent permitted by applicable law.
+
+You are responsible for validating the Model for your application and deployment environment. FireViewer models are research artifacts and must not be used alone to confirm a fire, trigger an emergency alert, order an evacuation or direct emergency response.
+
+## 9. Third-party terms
+
+Upstream and third-party components remain subject to their own licences and notices. If a third-party term independently imposes an obligation on your use of a component, that obligation remains applicable.
+
+## 10. Contact
+
+Commercial terms, official deployment formats and written permissions: **partenariats@fire-viewer.fr**

models/fireviewer_rfdetr_medium_v110_learning/CITATION.md

@@ -0,0 +1,7 @@
+# Citation and attribution
+
+Recommended commercial attribution:
+
+> Fire/smoke detection model by FireViewer — https://huggingface.co/fireviewer/fire-smoke-rfdetr-medium-v110-strict-v1
+
+Where practical, keep a direct link to the repository in technical documentation, credits, acknowledgements or legal notices. Upstream research citations remain applicable and should be retained in addition to FireViewer attribution.

models/fireviewer_rfdetr_medium_v110_learning/COMMERCIAL_USE.md

@@ -0,0 +1,20 @@
+# Commercial use — quick reference
+
+| Use | Status under FireViewer Model Use License v1.0 |
+|---|---|
+| Research / evaluation | Permitted |
+| Internal commercial evaluation | Permitted |
+| Commercial use with FireViewer attribution | Permitted |
+| Hosted API / SaaS where customers do not receive weights | Permitted with attribution |
+| Internal ONNX / TensorRT / LiteRT / quantization | Permitted |
+| Internal fine-tuning | Permitted |
+| Publishing a converted checkpoint | Not permitted |
+| Shipping the weights in a device or on-premise product | Not permitted |
+| Redistributing original weights | Not permitted |
+| Redistributing fine-tuned / quantized / converted weights | Not permitted |
+| Commercial use without public FireViewer attribution | Separate written agreement |
+| OEM / redistribution rights | Separate written agreement explicitly granting them |
+
+The full terms are in `CHECKPOINT_LICENSE.md`.
+
+FireViewer may publish additional official deployment formats when technically relevant, including ONNX, TensorRT, LiteRT/TFLite, FP16, INT8, NVFP4 or another target-specific format.

models/fireviewer_rfdetr_medium_v110_learning/README.md

@@ -0,0 +1,15 @@
+# FireViewer RF-DETR Medium 1.10 strict v1 — Android learning variant
+
+Source: `fireviewer/fire-smoke-rfdetr-medium-v110-strict-v1`, revision `901382d9c8eef2af8b4c13640413c03dbfdbeec2`.
+
+This is a real mutable LiteRT model with `infer`, `train`, `save`, and `restore` signatures. Training executes on Android using the image and reviewed targets. Trainable scope: **candidate_classification_and_box_adaptation_only**. The visual backbone remains frozen. Does not create proposals absent from frozen detector
+
+The original inference family is retained under `models/fireviewer_rfdetr_medium_v110`. This variant has its own explicit Android configuration.
+
+Variable image dimensions: `{'mode': 'bilinear_stretch_inside_graph', 'native_backbone_shape': [1, 3, 576, 576]}`. The Android configuration chooses a bounded input canvas; the image may have any original size. Images are processed individually, so a dataset need not have homogeneous dimensions.
+
+Checkpoints include parameters, momentum and step. Validation executed actual updates, changed parameters, closed/reopened the interpreter, restored identical predictions and reproduced the next optimizer update. See `training_validation.json`. Tests use synthetic supervision to verify execution and persistence; no accuracy or forgetting benchmark is claimed. Android device execution: `False`.
+
+Use LiteRT CPU with XNNPACK disabled and Select TF Ops for checkpoint operations. The default label space is retained; changing class count requires rebuilding the head with the supplied conversion sources. Use only human-reviewed labels for training. Retain replay examples and validate a candidate before activating it.
+
+Upstream licenses and attributions continue to apply.

models/fireviewer_rfdetr_medium_v110_learning/RIGHTS_AND_ATTRIBUTION.md

@@ -0,0 +1,9 @@
+# Rights and attribution
+
+This repository separates three layers:
+
+1. **Upstream implementation / base model** — RF-DETR Medium core model/package: Apache-2.0 upstream. Verify the exact pinned revision before remote publication of the final rights file.
+2. **Training corpus provenance** — `fireviewer/fire-smoke-detection-corpus-v1` and its source records.
+3. **FireViewer-trained checkpoint and FireViewer-published deployment artifacts** — governed by `CHECKPOINT_LICENSE.md` where that file is included.
+
+FireViewer grants only rights it is entitled to grant. Third-party notices and source-specific obligations remain applicable.

models/fireviewer_rfdetr_medium_v110_learning/THIRD_PARTY_NOTICES.md

@@ -0,0 +1,5 @@
+# Third-party notices
+
+RF-DETR licensing is split by upstream component. The Medium core family is documented upstream under Apache-2.0; XL/2XL Plus components use different terms and must not be conflated with this release.
+
+Preserve the exact RF-DETR upstream notices used by the checkpoint and the per-source FireViewer corpus rights.

models/fireviewer_rfdetr_medium_v110_learning/UPSTREAM_README.md

@@ -0,0 +1,61 @@
+---
+license: other
+pipeline_tag: object-detection
+datasets:
+- fireviewer/fire-smoke-detection-corpus-v1
+tags:
+- fireviewer
+- fire
+- smoke
+- wildfire
+- rfdetr
+- object-detection
+---
+
+# FireViewer RF-DETR Medium 1.10 strict v1
+
+Research release of an RF-DETR Medium detector trained for `smoke_visible` and `flame_visible`.
+
+## Status
+
+**Serious validation candidate; independent frozen benchmark pending.** The selected epoch-18 EMA checkpoint reports training-validation mAP50-95 **0.468331**, mAP50 **0.734626**, precision **0.755401**, recall **0.649472** and F1 **0.697713**. These are not directly rankable against D-FINE/RT-DETR/YOLO independent scores.
+
+Default inference candidate: `checkpoint_best_total.pth`. Resume checkpoint `checkpoint_23.ckpt` is retained for exact training continuation, not preferred serving.
+
+## Rights
+
+RF-DETR Medium is in Roboflow's Apache-2.0 core model family. Before applying FireViewer custom checkpoint terms remotely, verify that the repository's exact upstream revision and all included files are the Apache-designated core components. Training-source rights remain separate.
+
+## Safety
+
+This model is not a certified warning system and has not yet passed the current frozen independent FireViewer benchmark.
+
+## Reproducibility and artifact access
+
+```python
+from huggingface_hub import hf_hub_download
+
+path = hf_hub_download(
+    repo_id="fireviewer/fire-smoke-rfdetr-medium-v110-strict-v1",
+    repo_type="model",
+    revision="443ea24a73004558b288eb3b7d78d7b04cdd5cd4",
+    filename="checkpoint_best_total.pth",
+)
+```
+Hub artifact SHA-256 for `checkpoint_best_total.pth`: `47f6d478baa44622ec9075dbbfd98f04a80471f808536fa7b343615f3020ca46`. This identity was read from Hub metadata; the weights were not downloaded or rehashed during the documentation review.
+
+The example downloads a pinned artifact; it does not execute or qualify inference. Preserve the matching configuration, labels, preprocessing and runtime dependencies from that revision. Keep raw outputs, scores, model revision and source provenance when integrating with `fireviewer-vision-runtime`.
+
+RF-DETR version **1.10.0**, resolution **576**, selected EMA at epoch **18**. See [training configuration](training_config.json), [validation metrics](validation-metrics.json), [artifact roles](artifact-manifest.json) and `metrics.csv`. The exact training-source revision must be recovered from the retained run provenance before any reproduction; this card does not invent one. The `visibility: private` field in the original artifact manifest is historical; current Hub metadata is public.
+
+## Evaluation boundary
+
+The independent detector benchmark remains pending. Training-validation mAP, precision, recall and F1 are checkpoint-selection measurements, not an external ranking. An inference threshold shown in an example is not an operationally calibrated threshold. No new evaluation date or result is established by this update. Preserve the exact checkpoint, training split, grouping and source rights for the independent comparison. Human review remains required for sensitive results.
+
+## Documentation, revision and stewardship
+
+Documentation reviewed on **19 September 2026**, using the FireViewer documentation pack and the repository at [`443ea24a73004558b288eb3b7d78d7b04cdd5cd4`](https://huggingface.co/fireviewer/fire-smoke-rfdetr-medium-v110-strict-v1/tree/443ea24a73004558b288eb3b7d78d7b04cdd5cd4). This is a documentation and metadata check, not a new model evaluation, training run, data acquisition or full artifact verification. Historical receipts keep their original dates and identifiers; manifest hashes of earlier README versions describe those earlier releases.
+
+The association FIRE-VIEWER provides administrative and financial stewardship for resources under its control. Technical governance is maintainer-led. Pre-association rights, UWD components, upstream licences and source-specific rights remain separate; repository placement does not transfer ownership or grant new rights.
+
+[Canonical documentation](https://github.com/fireviewer/Fireviewer_doc/blob/main/docs/public/HUGGINGFACE.md) · [Status vocabulary](https://github.com/fireviewer/Fireviewer_doc/blob/main/docs/public/STATUTS_ET_VOCABULAIRE.md) · [Institutional website](https://fire-viewer.fr). Contact: **contact@fire-viewer.fr**.

models/fireviewer_rfdetr_medium_v110_learning/android_model_config.json

@@ -0,0 +1,58 @@
+{
+  "task": "object_detection",
+  "adapter": "yolo",
+  "inputWidth": 576,
+  "inputHeight": 576,
+  "inputLayout": "NCHW",
+  "inputType": "FLOAT32",
+  "mean": 0.0,
+  "std": 255.0,
+  "resizeMode": "stretch",
+  "labels": [
+    "smoke_visible",
+    "flame_visible"
+  ],
+  "threads": 2,
+  "outputIndex": 0,
+  "threshold": 0.1,
+  "scoreActivation": "none",
+  "dynamicMinSize": 128,
+  "dynamicMaxSize": 1280,
+  "dynamicStride": 1,
+  "outputLayout": "BCN",
+  "coordinates": "pixels",
+  "outputIndexBoxes": 0,
+  "outputIndexScores": 1,
+  "channelMean": [
+    123.675,
+    116.28,
+    103.53
+  ],
+  "channelStd": [
+    58.395,
+    57.12,
+    57.375
+  ],
+  "training": {
+    "targetEncoding": "boxes_xyxy_class_mask",
+    "targetShape": [
+      1,
+      100,
+      6
+    ],
+    "inferOutputs": [
+      "detections"
+    ],
+    "trainSignature": "train",
+    "inferSignature": "infer",
+    "saveSignature": "save",
+    "restoreSignature": "restore",
+    "imageInput": "x",
+    "targetInput": "y",
+    "lossOutput": "loss",
+    "checkpointInput": "checkpoint_path",
+    "learningRateInput": "learning_rate",
+    "scope": "candidate_classification_and_box_adaptation_only"
+  },
+  "isRgb": true
+}

models/fireviewer_rfdetr_medium_v110_learning/artifact_manifest.json

@@ -0,0 +1,46 @@
+{
+  "README.md": {
+    "sha256": "d9bff0f5082a744063b9a3fee74e970fa76a2b4ec26ca8ccd958216480df1104",
+    "bytes": 1730
+  },
+  "UPSTREAM_README.md": {
+    "sha256": "82ae0bc7bb5a01972105e2dabe6cfb584a579a21951112a89cd9b7699570a63d",
+    "bytes": 4341
+  },
+  "COMMERCIAL_USE.md": {
+    "sha256": "85cc7903902ecf421783a56a44005d53fc642436482a811ef3954f8a5b031c2c",
+    "bytes": 1104
+  },
+  "CHECKPOINT_LICENSE.md": {
+    "sha256": "549e691e53c816d605abc0acea77116ada8289dd9896dd67bebd3db317760b73",
+    "bytes": 4429
+  },
+  "CITATION.md": {
+    "sha256": "a2ec39ce635dc8de9bb32b76c341f169c2b608e6cea43caaa93e86e670e0d5f4",
+    "bytes": 421
+  },
+  "THIRD_PARTY_NOTICES.md": {
+    "sha256": "3045ff6e1ac8235766b8ebbf076bb14f7b9c954faad0ba107378ef2ad762fe16",
+    "bytes": 338
+  },
+  "RIGHTS_AND_ATTRIBUTION.md": {
+    "sha256": "cac183a2275d3d2a486c3cb773f05dcd90c80f913bcc674268386be2d85e3e27",
+    "bytes": 641
+  },
+  "runtime_contract.json": {
+    "sha256": "0ae50522665a1a6d45fd2df82e4cbf1d644994744f555ad12cbb4605ee8dd830",
+    "bytes": 3297
+  },
+  "training_validation.json": {
+    "sha256": "5ff911abe83bfa0b5541ffaa7ac497afb057d359865cf8e8baa1bf2857476a0e",
+    "bytes": 2467
+  },
+  "android_model_config.json": {
+    "sha256": "0fa7f165d9c08f6f16c65803cd92ef18b1583e881b68981b790e8cbeecc871ca",
+    "bytes": 1180
+  },
+  "model.tflite": {
+    "sha256": "ec9fafba09389249d816142196cc014dff8eaa0ea0163989e4b6bd67beae32a5",
+    "bytes": 124410420
+  }
+}

models/fireviewer_rfdetr_medium_v110_learning/model.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9fafba09389249d816142196cc014dff8eaa0ea0163989e4b6bd67beae32a5
+size 124410420

models/fireviewer_rfdetr_medium_v110_learning/runtime_contract.json

@@ -0,0 +1,117 @@
+{
+  "schema": 2,
+  "key": "fireviewer_rfdetr_medium_v110_learning",
+  "source_model": "fireviewer_rfdetr_medium_v110",
+  "task": "object_detection",
+  "upstream": "fireviewer/fire-smoke-rfdetr-medium-v110-strict-v1",
+  "upstream_revision": "901382d9c8eef2af8b4c13640413c03dbfdbeec2",
+  "backbone_frozen": true,
+  "training_scope": "candidate_classification_and_box_adaptation_only",
+  "report": {
+    "key": "fireviewer_rfdetr_medium_v110",
+    "validation_passed": true,
+    "training_scope": "candidate_classification_and_box_adaptation_only",
+    "backbone_frozen": true,
+    "limitation": "Does not create proposals absent from frozen detector",
+    "initial_detector_parity": true,
+    "parameters_changed": true,
+    "initial_loss": 0.8691307902336121,
+    "final_loss": 0.19148443639278412,
+    "mixed_image_shapes": [
+      [
+        224,
+        224
+      ],
+      [
+        224,
+        288
+      ],
+      [
+        288,
+        224
+      ]
+    ],
+    "restart_logits_exact": true,
+    "optimizer_resume_exact": true,
+    "variable_image_preprocessing": {
+      "mode": "bilinear_stretch_inside_graph",
+      "native_backbone_shape": [
+        1,
+        3,
+        576,
+        576
+      ]
+    },
+    "android_device_tested": false,
+    "accuracy_evaluated": false,
+    "sha256": "ec9fafba09389249d816142196cc014dff8eaa0ea0163989e4b6bd67beae32a5",
+    "bytes": 124410420,
+    "signatures": {
+      "infer": {
+        "inputs": [
+          "x"
+        ],
+        "outputs": [
+          "boxes",
+          "detections",
+          "logits"
+        ]
+      },
+      "restore": {
+        "inputs": [
+          "checkpoint_path"
+        ],
+        "outputs": [
+          "step"
+        ]
+      },
+      "save": {
+        "inputs": [
+          "checkpoint_path"
+        ],
+        "outputs": [
+          "step"
+        ]
+      },
+      "train": {
+        "inputs": [
+          "learning_rate",
+          "x",
+          "y"
+        ],
+        "outputs": [
+          "loss",
+          "step"
+        ]
+      },
+      "training_state": {
+        "inputs": [],
+        "outputs": [
+          "head_kernel",
+          "step"
+        ]
+      }
+    },
+    "runtime_requirement": "LiteRT builtin CPU; disable default XNNPACK delegates; Select TF Ops required for checkpoint Save/Restore",
+    "android_runtime_dependencies": [
+      "org.tensorflow:tensorflow-lite:2.16.1",
+      "org.tensorflow:tensorflow-lite-select-tf-ops:2.16.1"
+    ],
+    "frozen_backbone_sha256": "badcf1f0edbef2e6f319370ac7d5a2231d4332236656087f94b86376e73efcf9",
+    "head_initialization": "source_model_or_identity_adapter",
+    "conversion_source_sha256": {
+      "merge_training_graph.py": "93def8b746dd763c7ef703e29a5db3bab754716c6358bdda5acb64531b4c50ce",
+      "build_trainable_classifier.py": "9eef4cff03c30981e628c26aacfc3d7ed3183f5af4eef0feebe1c116e0fa7b92",
+      "build_trainable_detector.py": "397a99d9a048576542f9a0f1952c0c4b54c6f7c937aeecf72e0832a20c1746ff",
+      "build_trainable_heatmap.py": "94fb85124078035a177deb087442a4c130eff3c9032a2eef90fee9a122e40ddf"
+    }
+  },
+  "optimizer": "momentum SGD, momentum=0.9",
+  "checkpoint_contains": [
+    "trainable parameters",
+    "momentum buffers",
+    "global step"
+  ],
+  "requires_select_tf_ops": true,
+  "android_configuration": "android_model_config.json"
+}

models/fireviewer_rfdetr_medium_v110_learning/training_validation.json

@@ -0,0 +1,99 @@
+{
+  "key": "fireviewer_rfdetr_medium_v110",
+  "validation_passed": true,
+  "training_scope": "candidate_classification_and_box_adaptation_only",
+  "backbone_frozen": true,
+  "limitation": "Does not create proposals absent from frozen detector",
+  "initial_detector_parity": true,
+  "parameters_changed": true,
+  "initial_loss": 0.8691307902336121,
+  "final_loss": 0.19148443639278412,
+  "mixed_image_shapes": [
+    [
+      224,
+      224
+    ],
+    [
+      224,
+      288
+    ],
+    [
+      288,
+      224
+    ]
+  ],
+  "restart_logits_exact": true,
+  "optimizer_resume_exact": true,
+  "variable_image_preprocessing": {
+    "mode": "bilinear_stretch_inside_graph",
+    "native_backbone_shape": [
+      1,
+      3,
+      576,
+      576
+    ]
+  },
+  "android_device_tested": false,
+  "accuracy_evaluated": false,
+  "sha256": "ec9fafba09389249d816142196cc014dff8eaa0ea0163989e4b6bd67beae32a5",
+  "bytes": 124410420,
+  "signatures": {
+    "infer": {
+      "inputs": [
+        "x"
+      ],
+      "outputs": [
+        "boxes",
+        "detections",
+        "logits"
+      ]
+    },
+    "restore": {
+      "inputs": [
+        "checkpoint_path"
+      ],
+      "outputs": [
+        "step"
+      ]
+    },
+    "save": {
+      "inputs": [
+        "checkpoint_path"
+      ],
+      "outputs": [
+        "step"
+      ]
+    },
+    "train": {
+      "inputs": [
+        "learning_rate",
+        "x",
+        "y"
+      ],
+      "outputs": [
+        "loss",
+        "step"
+      ]
+    },
+    "training_state": {
+      "inputs": [],
+      "outputs": [
+        "head_kernel",
+        "step"
+      ]
+    }
+  },
+  "runtime_requirement": "LiteRT builtin CPU; disable default XNNPACK delegates; Select TF Ops required for checkpoint Save/Restore",
+  "android_runtime_dependencies": [
+    "org.tensorflow:tensorflow-lite:2.16.1",
+    "org.tensorflow:tensorflow-lite-select-tf-ops:2.16.1"
+  ],
+  "frozen_backbone_sha256": "badcf1f0edbef2e6f319370ac7d5a2231d4332236656087f94b86376e73efcf9",
+  "head_initialization": "source_model_or_identity_adapter",
+  "conversion_source_sha256": {
+    "merge_training_graph.py": "93def8b746dd763c7ef703e29a5db3bab754716c6358bdda5acb64531b4c50ce",
+    "build_trainable_classifier.py": "9eef4cff03c30981e628c26aacfc3d7ed3183f5af4eef0feebe1c116e0fa7b92",
+    "build_trainable_detector.py": "397a99d9a048576542f9a0f1952c0c4b54c6f7c937aeecf72e0832a20c1746ff",
+    "build_trainable_heatmap.py": "94fb85124078035a177deb087442a4c130eff3c9032a2eef90fee9a122e40ddf"
+  }
+}