1.8.3

## 📋 Summary

RF-DETR 1.8.3 is a focused patch release with one new capability and three correctness fixes. The headline addition is **`optimize_for_inference(inplace=True)`** — a memory-efficient inference path that skips the deep-copy of the base model, useful on memory-constrained GPUs and edge devices. On the bug-fix side: **keypoint horizontal-flip augmentation now correctly swaps left/right pairs** (previously labels were corrupted on flip); **bounding boxes are clamped to image bounds** so objects at image edges no longer produce negative or out-of-frame coordinates; and **default loss coefficients for segmentation and keypoint fine-tuning are restored** to their intended values after a regression introduced in v1.7.

## ✨ Spotlights

### In-place inference optimization

`optimize_for_inference(inplace=True)` exports the model using the loaded weights directly — no deep-copy — reducing peak memory during the optimization step by roughly 0.5× model weight. After inplace optimization, the base model is cleared: `export()` raises `RuntimeError` and `remove_optimized_model()` issues a `UserWarning` and returns cleanly. The new `is_optimized_inplace` property lets you check the current state.

```python
model = RFDETRSmall()

# Default: deep-copy kept, fully reversible
model.optimize_for_inference(compile=False, dtype="float16")
model.remove_optimized_model()  # works fine

# New: inplace, lowest possible memory — irreversible
model.optimize_for_inference(compile=False, inplace=True, dtype="float16")
print(model.is_optimized_inplace)  # True
```

### Correct keypoint flip augmentation

Keypoint training now correctly swaps symmetric pairs during horizontal flip augmentation. `CocoKeypointSchema` and `YoloKeypointSchema` both gain a `keypoint_flip_pairs` field, populated automatically from keypoint names (COCO left/right convention) or from `flip_idx` (YOLO pose). `infer_coco_keypoint_schema` and `infer_yolo_keypoint_schema` are also re-exported from the public `rfdetr.datasets` namespace.

```python
from rfdetr.datasets import infer_coco_keypoint_schema  # now public

schema = infer_coco_keypoint_schema("path/to/_annotations.coco.json")
print(schema.keypoint_flip_pairs)  # [1, 2, 3, 4, ...] — auto-inferred

model.train(dataset_dir=DATASET_DIR, epochs=50, keypoint_schema=schema)
```

Native COCO format (`dataset_file="coco"`) is supported alongside `"roboflow"` and `"yolo"`.

### Bounding box coordinates clamped to image bounds

Predicted boxes are now guaranteed to lie within `[0, width] × [0, height]`. Model regression output is unbounded — objects near image edges could previously produce negative `x1`/`y1` or `x2`/`y2` values exceeding image dimensions. `scale_fct` is also cast to `boxes.dtype` to avoid dtype mismatch with fp16 inference.

### Loss coefficient defaults corrected

Two training config defaults were silently wrong since v1.7:

- `SegmentationTrainConfig.cls_loss_coef` was `5.0` — now `1.0`, restoring the effective weight from before the v1.7 `TrainConfig` ownership migration.
- `KeypointTrainConfig.keypoint_nll_loss_coef` was `0.5` — now `1.0`, aligning the NLL term with all other keypoint loss weights.

If your current fine-tuned runs relied on the old defaults, pass the values explicitly to maintain continuity.

## 🔄 Migration guide

No breaking API changes in this release.

**Segmentation fine-tuning — `cls_loss_coef` default change**: if you fine-tune segmentation models without setting `cls_loss_coef` explicitly, your loss balance shifts. To reproduce prior runs:

```python
from rfdetr.config import SegmentationTrainConfig

config = SegmentationTrainConfig(cls_loss_coef=5.0)
```

**Keypoint fine-tuning — `keypoint_nll_loss_coef` default change**: to reproduce prior runs:

```python
from rfdetr.config import KeypointTrainConfig

config = KeypointTrainConfig(keypoint_nll_loss_coef=0.5)
```

**Keypoint horizontal-flip augmentation now active**: flip augmentation was disabled for keypoints in v1.8.1 because pair swapping was not yet implemented. With this release it is enabled automatically when `keypoint_flip_pairs` is non-empty. Datasets without left/right keypoint naming conventions infer zero pairs and skip `ReplayCompose` automatically — no action required.

## 📝 Notable changes

### 🚀 Added

- **`optimize_for_inference(inplace=True)`** — keyword-only arg on `RFDETR.optimize_for_inference()`; skips deep-copy for memory-constrained inference-only deployments. Requires `compile=False`. ([#1089](https://github.com/roboflow/rf-detr/pull/1089))
- **`RFDETR.is_optimized_inplace`** — property returning `True` after a successful inplace optimization. ([#1089](https://github.com/roboflow/rf-detr/pull/1089))
- **`CocoKeypointSchema.keypoint_flip_pairs`** and **`YoloKeypointSchema.keypoint_flip_pairs`** — flat list of horizontal-flip swap pairs, inferred from keypoint names (COCO) or `flip_idx` (YOLO). ([#1164](https://github.com/roboflow/rf-detr/pull/1164))
- **`infer_coco_keypoint_schema`** and **`infer_yolo_keypoint_schema`** re-exported from `rfdetr.datasets` (public namespace). ([#1164](https://github.com/roboflow/rf-detr/pull/1164))

### 🌱 Changed

- Horizontal flip detection in `AlbumentationsWrapper` now uses Albumentations `ReplayCompose` replay metadata instead of heuristic bbox-center mirroring; eliminates false positives. Falls back to `alb.Compose` with a `UserWarning` on `albumentations <1.3`. ([#1164](https://github.com/roboflow/rf-detr/pull/1164))
- Keypoint schema inference now supports native COCO format (`dataset_file="coco"`) alongside `"roboflow"` and `"yolo"`. ([#1164](https://github.com/roboflow/rf-detr/pull/1164))
- `_keypoint_schema_cache` key changed from `dataset_dir` to `(dataset_file, dataset_dir)` tuple to prevent cross-format cache collisions. ([#1164](https://github.com/roboflow/rf-detr/pull/1164))
- `SegmentationTrainConfig.cls_loss_coef` default: `5.0` → `1.0`. ([#1165](https://github.com/roboflow/rf-detr/pull/1165))
- `KeypointTrainConfig.keypoint_nll_loss_coef` default: `0.5` → `1.0`. ([#1165](https://github.com/roboflow/rf-detr/pull/1165))

### 🔧 Fixed

- Predicted bounding boxes clamped to `[0, width] × [0, height]` in `PostProcess._postprocess_boxes()`; `scale_fct` also cast to `boxes.dtype` for fp16 safety. ([#1168](https://github.com/roboflow/rf-detr/pull/1168))
- `SegmentationTrainConfig.cls_loss_coef` default corrected from `5.0` to `1.0` — restores the pre-v1.7 effective classification loss weight. ([#1165](https://github.com/roboflow/rf-detr/pull/1165))
- `KeypointTrainConfig.keypoint_nll_loss_coef` default restored to `1.0`. ([#1165](https://github.com/roboflow/rf-detr/pull/1165))
- `optimize_for_inference()` flag ordering fixed: `_optimized_inplace` set before `model.model = None` so exception recovery sees correct state. ([#1089](https://github.com/roboflow/rf-detr/pull/1089))
- `remove_optimized_model()` now issues `UserWarning` and returns cleanly after inplace optimization instead of raising `RuntimeError`. ([#1089](https://github.com/roboflow/rf-detr/pull/1089))
- `export()` now raises `RuntimeError` immediately if called after inplace optimization. ([#1089](https://github.com/roboflow/rf-detr/pull/1089))

---

## 🏆 Contributors

- **Jonas Pirner** (@pirnerjonas) — added in-place inference optimization for memory-efficient deployment
- **Alessandro Brunello** (@Armaggheddon, [LinkedIn](https://www.linkedin.com/in/brunelloalessandro)) — fixed postprocessor to clamp predicted boxes to image bounds
- **Jirka Borovec** (@Borda, [LinkedIn](https://www.linkedin.com/in/jirka-borovec/)) — restored loss coefficient defaults, fixed keypoint flip-pair augmentation, restructured test layout

---

**Full changelog**: https://github.com/roboflow/rf-detr/compare/1.8.2...1.8.3