oriented-det 0.1.0__py3-none-any.whl

oriented_det/utils/viz.py

@@ -0,0 +1,181 @@
+"""Visualization helpers for geometric primitives."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Iterable, List, Sequence, Tuple
+import itertools
+import math
+import random
+
+try:  # Optional dependency; only required when drawing actual images.
+    from PIL import Image, ImageDraw, ImageFont
+except Exception:  # pragma: no cover - exercised when pillow is not installed.
+    Image = None  # type: ignore[assignment]
+    ImageDraw = None  # type: ignore[assignment]
+    ImageFont = None  # type: ignore[assignment]
+
+from ..geometry import Polygon, QBox, RBox
+
+Point = Tuple[float, float]
+Color = Tuple[int, int, int]
+
+DEFAULT_PALETTE = [
+    (253, 128, 93),
+    (44, 160, 44),
+    (31, 119, 180),
+    (148, 103, 189),
+    (214, 39, 40),
+    (140, 86, 75),
+    (188, 189, 34),
+    (23, 190, 207),
+]
+
+
+def as_polygon(obj) -> Polygon:
+    if isinstance(obj, Polygon):
+        return obj
+    if isinstance(obj, QBox):
+        return obj.to_polygon()
+    if isinstance(obj, RBox):
+        return obj.to_polygon()
+    return Polygon(obj)
+
+
+def cycle_palette(n: int, *, palette: Sequence[Color] | None = None) -> List[Color]:
+    palette = palette or DEFAULT_PALETTE
+    if not palette:
+        raise ValueError("Palette cannot be empty.")
+    repeated = list(itertools.islice(itertools.cycle(palette), n))
+    return repeated
+
+
+def random_palette(n: int, seed: int | None = None) -> List[Color]:
+    rng = random.Random(seed)
+    return [(rng.randint(0, 255), rng.randint(0, 255), rng.randint(0, 255)) for _ in range(n)]
+
+
+def format_label(label: str, score: float | None = None) -> str:
+    return f"{label} ({score:.2f})" if score is not None else label
+
+
+@dataclass
+class DrawingSpec:
+    """Parameters controlling drawing appearance."""
+
+    outline: Color = (255, 255, 255)
+    fill: Color | None = None
+    width: int = 2
+
+
+def _ensure_pil_image(image):
+    if Image is None or ImageDraw is None:
+        raise RuntimeError("Pillow is required for drawing visualizations.")
+    if isinstance(image, Image.Image):
+        return image.convert("RGB")
+    try:
+        import numpy as np
+
+        if isinstance(image, np.ndarray):
+            return Image.fromarray(image.astype("uint8"), "RGB")
+    except Exception:  # pragma: no cover - optional dependency
+        pass
+    raise TypeError("image must be a PIL.Image or a numpy array.")
+
+
+def _polygon_centroid(poly_pts: Sequence[Sequence[float]]) -> Tuple[float, float]:
+    """Return (cx, cy) centroid of polygon points."""
+    pts = [tuple(map(float, pt)) for pt in poly_pts]
+    if not pts:
+        return (0.0, 0.0)
+    n = len(pts)
+    cx = sum(p[0] for p in pts) / n
+    cy = sum(p[1] for p in pts) / n
+    return (cx, cy)
+
+
+def _polygon_top_anchor(poly_pts: Sequence[Sequence[float]], offset: float = 2.0) -> Tuple[float, float]:
+    """Return (x, y) position for label at the top of the polygon (smallest y = top in image coords).
+    Uses the midpoint of the top edge so the label sits near the top without obscuring the box content.
+    """
+    pts = [tuple(map(float, pt)) for pt in poly_pts]
+    if not pts:
+        return (0.0, 0.0)
+    sorted_by_y = sorted(pts, key=lambda p: p[1])
+    top_two = sorted_by_y[:2]
+    mx = (top_two[0][0] + top_two[1][0]) / 2
+    my = (top_two[0][1] + top_two[1][1]) / 2
+    return (mx, my - offset)
+
+
+def draw_polygons(
+    image,
+    polygons: Iterable[Sequence[Sequence[float]]],
+    specs: Sequence[DrawingSpec] | None = None,
+    labels: Iterable[str] | None = None,
+    label_color: Color = (255, 255, 255),
+):
+    """Draw polygons on image, optionally with text labels near the top of each polygon.
+
+    Args:
+        image: PIL Image or numpy array (RGB).
+        polygons: Iterable of polygon point lists.
+        specs: Optional drawing specs (outline, fill, width) per polygon.
+        labels: Optional list of text labels; if provided, length must match polygons.
+        label_color: RGB color for label text (default white).
+
+    Returns:
+        PIL Image with polygons and labels drawn.
+    """
+    pil_img = _ensure_pil_image(image)
+    draw = ImageDraw.Draw(pil_img, "RGBA")
+    polygons = list(polygons)
+    specs = specs or [DrawingSpec(outline=color) for color in cycle_palette(len(polygons) or 1)]
+    if len(specs) != len(polygons):
+        raise ValueError("specs length must match polygons length.")
+    labels_list = list(labels) if labels is not None else None
+    if labels_list is not None and len(labels_list) != len(polygons):
+        raise ValueError("labels length must match polygons length when provided.")
+    font = None
+    if ImageFont is not None:
+        for path in (
+            "/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
+            "/usr/share/fonts/truetype/liberation/LiberationSans-Regular.ttf",
+        ):
+            try:
+                font = ImageFont.truetype(path, 10)
+                break
+            except Exception:
+                continue
+        if font is None:
+            try:
+                font = ImageFont.load_default()
+            except Exception:
+                pass
+    for i, (poly_pts, spec) in enumerate(zip(polygons, specs)):
+        pts = [tuple(map(float, pt)) for pt in poly_pts]
+        if spec.fill:
+            draw.polygon(pts, fill=spec.fill + (64,))
+        draw.line(pts + [pts[0]], fill=spec.outline, width=spec.width)
+        if labels_list is not None and i < len(labels_list) and labels_list[i]:
+            x, y = _polygon_top_anchor(poly_pts)
+            kwargs = {"fill": label_color}
+            if font is not None:
+                kwargs["font"] = font
+            draw.text((x, y), labels_list[i], **kwargs)
+    return pil_img
+
+
+def draw_boxes(image, boxes: Iterable[RBox | QBox | Sequence[float]], **kwargs):
+    polygons = [as_polygon(box).points for box in boxes]
+    return draw_polygons(image, polygons, **kwargs)
+
+
+__all__ = [
+    "cycle_palette",
+    "random_palette",
+    "format_label",
+    "DrawingSpec",
+    "draw_polygons",
+    "draw_boxes",
+]

oriented_det-0.1.0.dist-info/METADATA

@@ -0,0 +1,313 @@
+Metadata-Version: 2.4
+Name: oriented-det
+Version: 0.1.0
+Summary: A lightweight, modern PyTorch library for rotated object detection in aerial and satellite imagery
+Author: Jeff Faudi, DL4EO
+Maintainer: Jeff Faudi, DL4EO
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/DL4EO/oriented-det
+Project-URL: Documentation, https://github.com/DL4EO/oriented-det#readme
+Project-URL: Repository, https://github.com/DL4EO/oriented-det
+Project-URL: Issues, https://github.com/DL4EO/oriented-det/issues
+Project-URL: Bug Tracker, https://github.com/DL4EO/oriented-det/issues
+Project-URL: DL4EO, https://dl4eo.com
+Keywords: computer-vision,object-detection,rotated-detection,oriented-detection,pytorch,aerial-imagery,satellite-imagery,remote-sensing,dota,geospatial
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Image Recognition
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.3.0
+Requires-Dist: torchvision>=0.18.0
+Requires-Dist: numpy<2
+Requires-Dist: Pillow>=9.0
+Requires-Dist: albumentations>=1.3.0
+Requires-Dist: tqdm>=4.65.0
+Requires-Dist: tensorboard>=2.10
+Requires-Dist: matplotlib>=3.5.0
+Requires-Dist: huggingface_hub>=0.20.0
+Requires-Dist: shapely>=2.0.0
+Provides-Extra: export
+Requires-Dist: onnx>=1.14.0; extra == "export"
+Requires-Dist: onnxruntime>=1.16.0; extra == "export"
+Requires-Dist: onnx2tf>=1.22.0; extra == "export"
+Requires-Dist: tensorflow>=2.14.0; extra == "export"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Requires-Dist: black>=23.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: build>=1.0; extra == "dev"
+Requires-Dist: twine>=5.0; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: mkdocs>=1.5.0; extra == "docs"
+Requires-Dist: mkdocs-material>=9.0.0; extra == "docs"
+Requires-Dist: mkdocstrings[python]>=0.23.0; extra == "docs"
+Requires-Dist: pymdown-extensions>=10.0; extra == "docs"
+Provides-Extra: all
+Requires-Dist: oriented-det[dev]; extra == "all"
+Dynamic: license-file
+
+# OrientedDet
+
+**OrientedDet** is a lightweight, modern PyTorch library for **rotated object detection** in aerial and satellite imagery. It focuses on clean geometry, reliable operators, simple datasets, and practical baseline models—without the complexity of large detection frameworks. OrientedDet is designed for researchers, practitioners, and geospatial developers who need accurate rotation-aware detectors with a minimal API.
+
+## Features
+
+- **Geometry**: Rotated bounding boxes (rbox: cx, cy, w, h, angle), quadrilateral boxes (qbox), polygon ↔ rbox ↔ hbox conversions, angle normalization (le90, 0–180°), flip/rotate/scale transforms, visualization helpers
+- **IoU & NMS**: Rotated IoU and oriented NMS (CPU with optional GPU kernels when available); AABB pre-filtering; `obb_to_xyxy` / HBB conversion
+- **Datasets**: DOTA polygon loader (pattern, split file, or separate folders), image tiling, label filtering, ignore masks, oriented mAP evaluation
+- **Models**: **Oriented R-CNN** (horizontal RPN + MidpointOffset → oriented ROI), **Rotated Faster R-CNN** (oriented RPN + oriented ROI), **Rotated RetinaNet** (oriented anchors, focal loss); ResNet + FPN backbones; selective loading of external checkpoints where configs wire `checkpoint.load_from_checkpoint`
+- **Training**: JSON configs + **`odet train`**, mixed precision (AMP), gradient accumulation, checkpointing, best-metric tracking, TensorBoard, optional curriculum learning and profiling
+
+## Installation
+
+- **Python** >= 3.9. Use [uv](https://docs.astral.sh/uv/) to install Python versions and manage the virtual environment.
+- From the repo root (Linux with CUDA 12.1):
+
+```bash
+# Make sure you're in the project directory
+cd ~/oriented-det
+
+# Install uv if needed: https://docs.astral.sh/uv/getting-started/installation/
+# Create a venv with Python 3.12 (uv downloads the interpreter if missing)
+uv venv --python 3.12
+source .venv/bin/activate
+
+# Install PyTorch with CUDA 12.1 from PyTorch's index (2.3.0 or a higher version is fine)
+uv pip install "torch>=2.3.0" "torchvision>=0.18.0" --index-url https://download.pytorch.org/whl/cu121
+
+# Install dependencies and the project in editable mode
+uv pip install -r requirements.txt
+uv pip install -e .
+```
+
+- From PyPI (when published): `pip install oriented-det`
+- For development and tests: `uv pip install -e ".[dev]"`
+- For **macOS Apple Silicon** or **CPU-only**, see [Installation](docs/getting-started/installation.md).
+- Verify: `pytest tests/test_geometry.py tests/test_iou.py tests/test_nms.py`
+
+## Quick start
+
+After [installation](#installation):
+
+```bash
+# Train on DOTA tiles (edit dataset paths in the config first)
+odet train --config configs/rotated_faster_rcnn/dota_le90_3x.json
+
+# Or use the Makefile wrapper (same default config)
+make train
+```
+
+Default 3× recipe: `configs/rotated_faster_rcnn/dota_le90_3x.json` (see [configs/rotated_faster_rcnn/README.md](configs/rotated_faster_rcnn/README.md)). 1× baseline: `dota_le90_1x.json`.
+
+Programmatic APIs and a longer walkthrough: [Getting Started](docs/getting-started/installation.md). Config fields: [Configuration](docs/user-guide/configuration.md).
+
+### Paths in documentation and configs
+
+Examples throughout this repo use placeholder paths such as **`/path/to/data`** and **`/path/to/oriented-det`**. You can point commands and JSON configs at your real locations (e.g. `dataset.data_root` in a training config), or keep those placeholders and map them with symbolic links:
+
+```bash
+# Create the parent directory (may need sudo for paths under /path/to)
+sudo mkdir -p /path/to
+
+# Point the placeholder at your DOTA dataset
+ln -s /home/username/dota /path/to/data
+
+# Point the placeholder at your clone of this repo
+ln -s /home/username/oriented-det /path/to/oriented-det
+```
+
+After that, copy-pasted commands and unmodified configs that reference `/path/to/data` or `/path/to/oriented-det` resolve to your machine. Use relative symlink targets when you want the link to stay valid if the parent directory moves.
+
+## Repository layout
+
+| What | Where | You use it for |
+|------|--------|----------------|
+| **Library** | [`oriented_det/`](oriented_det/) | Geometry, models, datasets, training engine, ops — import in Python or extend in your own code |
+| **CLI** | **`odet`** ([`oriented_det/cli/`](oriented_det/cli/)) | Train, tile data, run val inference, metrics, demos — **primary interface** after `uv pip install -e .` |
+| **CLI implementations** | [`tools/`](tools/) | Python modules that implement `odet` subcommands (train, preds, tiling, …). Not a separate “old” API; contributors and debugging may call `python -m tools.train` directly |
+| **Configs** | [`configs/`](configs/) | Experiment JSON (`_base_` inheritance, schema in `configs/config.schema.json`) |
+| **Runs** | `runs/<model_type>/<timestamp>/` | Checkpoints, `config.json` snapshot, `train.log` (created at train time; not shipped in the repo) |
+| **Docs** | [`docs/`](docs/) | MkDocs user guide and API reference |
+| **Export** | [`export/`](export/) | Optional ONNX / TensorFlow export pipeline |
+| **Examples** | [`demo/`](demo/), [`pretrained/`](pretrained/) | Demo images; registered checkpoints (large `.pth` files are usually gitignored) |
+
+**`odet` vs `tools/`:** Installing the package registers the `odet` command. It loads modules under `tools/` (for example `tools.train`, `tools.save_predictions`). Shared inference and collate code lives in [`oriented_det/runtime/`](oriented_det/runtime/). You do not need two workflows — use **`odet`** (or **`make`**, which calls `odet`).
+
+**Publishing a clean tree:** Ship the library, configs, docs, and tests. Omit local experiment output (`runs/`), datasets, and machine-specific paths in configs/Makefile.
+
+## Documentation
+
+Full documentation is in the **docs/** folder and can be built and served with MkDocs:
+
+- **Build/serve**: `make docs` or `make docs-serve` (see [docs/README.md](docs/README.md)); or `uv pip install -e ".[docs]"` then `mkdocs serve`.
+- **Guides**: [Getting Started](docs/getting-started/installation.md), [User Guide](docs/user-guide/geometry.md), [API Reference](docs/api/geometry.md), [Examples](docs/examples/visualization.md).
+
+## Documentation by folder
+
+| Folder | README | Description |
+|--------|--------|-------------|
+| [export/](export/) | [export/README.md](export/README.md) | Phase 1: PyTorch → ONNX → Keras detect bundle; `cd export && make export-tf` |
+| [demo/](demo/) | [demo/README.md](demo/README.md) | Demo images; `odet image-demo` or `make demo` with the latest `runs/` checkpoint |
+| [pretrained/](pretrained/) | [pretrained/README.md](pretrained/README.md) | Registered checkpoints for fine-tunes; large `.pth` files are usually gitignored |
+| [oriented_det/cli/](oriented_det/cli/) | [oriented_det/cli/README.md](oriented_det/cli/README.md) | **`odet`** entry point and subcommand list |
+| [tools/](tools/) | [tools/README.md](tools/README.md) | CLI script implementations (invoked by `odet`; see [Repository layout](#repository-layout)) |
+| [configs/](configs/) | [configs/README.md](configs/README.md) | DOTA configs and **pretrain model zoo** (`_base_` inheritance) |
+| [deploy/example/](deploy/example/) | [deploy/example/README.md](deploy/example/README.md) | Minimal DOTA deploy smoke image |
+| [docs/](docs/) | [docs/README.md](docs/README.md) | MkDocs source; full user guide and API reference |
+
+## Training and evaluation
+
+Install once: `uv pip install -e .`. Then:
+
+| Task | Command |
+|------|---------|
+| Train | `odet train --config configs/rotated_faster_rcnn/dota_le90_3x.json` or `make train` |
+| Multi-GPU | `make train-multi-gpu` (`torchrun` + cuDNN on `LD_LIBRARY_PATH`) |
+| Tile DOTA | `odet tile-dota /path/to/dota/train` |
+| Val predictions | `odet preds --experiment-dir runs/rotated_faster_rcnn/<timestamp>` or `make preds` |
+| Offline mAP | `make eval-val` or `make preds` then `make metrics` |
+
+DOTA configs: per-model `dota_le90_1x.json` / `dota_le90_3x.json` under [configs/](configs/). Run `odet --help` for all subcommands. Makefile shortcuts and script-level options: [tools/README.md](tools/README.md). Config reference: [docs/user-guide/configuration.md](docs/user-guide/configuration.md), [configs/config.schema.json](configs/config.schema.json), [configs/README.md](configs/README.md).
+
+## Pretrained weights and evaluation
+
+- Place exported best checkpoints under **`pretrained/`** or use Hub slugs (`odet pretrained download oriented_rcnn_dota_le90_1x`). See [pretrained/README.md](pretrained/README.md) and [configs/README.md](configs/README.md#dota-pretrained-models-model-zoo).
+- **Tiled validation:** after training, run `make preds` then `make metrics` (or `odet preds` / `odet preds --metrics-from-json`). Large images use sliding-window inference when they exceed the model canvas; thresholds and overlap come from **`production.*`** in the experiment config.
+
+## Important notes
+
+- **Angles**: Radians; use a single convention (e.g. le90 for DOTA). Helper: `normalize_le90` from `oriented_det.geometry`. For angle-delta normalization in custom code, see `oriented_det.models.oriented_rpn.normalize_angle_delta`.
+- **NMS**: `torchvision.ops.nms_rotated` does not exist; the project uses a Python-based oriented NMS with AABB pre-filtering. GPU kernels are used when available.
+- **ROI/memory**: Training samples 512 proposals per image; use `roi_chunk_size` and `roi_use_checkpoint` for memory tuning on large GPUs.
+
+## Roadmap
+
+- **v0.1** (current): Geometry, IoU/NMS, DOTA loader + tiler, three baseline detectors, config-based training, Hub pretrained weights
+- **Next**: HRSC2016 dataset support, expanded tutorials, hosted docs
+- **Future**: Additional oriented detectors (e.g. FAIR1M), optional fused CUDA kernels
+
+## Contributing
+
+Contributions are welcome. Run tests with `pytest`, format with `black` and `ruff`. See [docs/contributing.md](docs/contributing.md) for guidelines.
+
+## Publishing to PyPI
+
+Version **0.1.0** — tag releases as **`v0.1.0`** (git) matching `version` in `pyproject.toml`.
+
+Configs: edit **`configs/`** at the repo root, then **`make sync-configs`** so **`oriented_det/configs/`** stays in sync (see **`oriented_det/configs/vendored_manifest.txt`**). CI runs **`make check-configs`**.
+
+Install publishing tools (included in `.[dev]`):
+
+```bash
+uv pip install -e ".[dev]"   # or: make publish-deps
+```
+
+### Step-by-step: first release (v0.1.0)
+
+#### 1. One-time PyPI setup
+
+1. Create accounts on [test.pypi.org](https://test.pypi.org) and [pypi.org](https://pypi.org) (can use the same email).
+2. **Register the project name** `oriented-det` on PyPI (first upload creates it; TestPyPI is separate).
+3. **Trusted Publishing (recommended)** — on each index, add a publisher for `DL4EO/oriented-det`, workflow `publish.yml`, environments `testpypi` / `pypi`. See [.github/workflows/README.md](.github/workflows/README.md).
+4. **Or API tokens** — create `pypi-…` tokens and export locally (or add GitHub secrets `TESTPYPI_API_TOKEN`, `PYPI_API_TOKEN`):
+
+```bash
+export TWINE_USERNAME=__token__
+export TWINE_PASSWORD=pypi-AgEI…   # TestPyPI or PyPI token
+```
+
+#### 2. Pre-release checklist
+
+```bash
+make check-configs
+pytest tests/ -q
+```
+
+Bump version in `pyproject.toml` and `docs/changelog.md` if needed (currently **0.1.0**).
+
+#### 3. Build locally
+
+```bash
+make sync-configs   # after changing configs/ or the manifest
+make build          # check-configs + sdist + wheel into dist/
+make twine-check
+```
+
+Smoke-test the wheel:
+
+```bash
+python -m venv /tmp/odet-smoke && source /tmp/odet-smoke/bin/activate
+pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
+pip install dist/*.whl
+odet --help
+python -c "from oriented_det.geometry import RBox; print(RBox(0,0,1,1,0).area)"
+```
+
+#### 4. Upload to TestPyPI
+
+```bash
+make publish-testpypi
+```
+
+Install from TestPyPI (PyPI index still needed for dependencies like `torch`):
+
+```bash
+pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple oriented-det==0.1.0
+odet --help
+```
+
+Or trigger **Actions → Publish → Run workflow** (target: `testpypi`) after configuring Trusted Publishing or secrets.
+
+#### 5. Tag and upload to production PyPI
+
+When TestPyPI looks good:
+
+```bash
+git tag -a v0.1.0 -m "Release 0.1.0"
+git push origin v0.1.0          # triggers publish.yml → PyPI (if CI is configured)
+```
+
+Local upload (fallback):
+
+```bash
+make publish-pypi
+```
+
+Create a [GitHub Release](https://github.com/DL4EO/oriented-det/releases) from tag `v0.1.0` with notes from `docs/changelog.md`.
+
+#### 6. After publish
+
+- Change install docs from “when published” to `pip install oriented-det`.
+- Users still install **PyTorch** separately for their CUDA/CPU platform.
+
+### Makefile targets
+
+| Target | Action |
+|--------|--------|
+| `make publish-deps` | Install `build` and `twine` |
+| `make build` | `check-configs` + `python -m build` |
+| `make twine-check` | Validate `dist/*` metadata |
+| `make publish-testpypi` | Build, check, upload to TestPyPI |
+| `make publish-pypi` | Build, check, upload to PyPI |
+
+Notes:
+
+- **Trusted Publishing** avoids long-lived tokens; keep `make publish-*` for manual releases. Details: [.github/workflows/README.md](.github/workflows/README.md).
+
+## License
+
+**Apache-2.0** — Copyright © Jeff Faudi and [DL4EO](https://dl4eo.com). See [LICENSE](LICENSE) for details.
+
+## Acknowledgements
+
+Design and APIs are informed by MMRotate, MMDetection, Detectron2, and related work in oriented object detection; **pretrained checkpoints in `pretrained/` are OrientedDet exports from this codebase**, not MMRotate zoo bundles.

oriented_det-0.1.0.dist-info/RECORD

@@ -0,0 +1,115 @@
+export/__init__.py,sha256=NZFHEjggrllpQwlJpPhj836_AJPCtSjDpVpetPFCJLk,189
+export/ort_runtime.py,sha256=xU9QOd6An4LCaJFCG6rkU-E8lU2WsMTC-dqm4D7yt_4,2519
+export/postprocess.py,sha256=nkRyciL3Hkjair02PyKrFK8_FQn3HLf0cOdu02qH0vs,5561
+export/tf_serving_model.py,sha256=0svldtGyXYtuQiawy7ck1nTd8DDZqntlteGSR-5ZHhA,3345
+export/val_dataset.py,sha256=Wr_0oQRTotse2UWkNYETzCNWiRfIBs62rqypuS-nk4E,5242
+export/wrappers.py,sha256=B8t0NH6hhAx3cZMgWhU65AZybxZb34ma_5qCqJPjx18,6126
+export/scripts/__init__.py,sha256=ml2MwROXcUgXIuj5qm6zE0Xxg4I2aeucHelJ2b51W5A,96
+export/scripts/build_faster_rcnn_savedmodel.py,sha256=yag46p5VF6WRDhVR8NklvQJ6YXa5eUYVHfgfop3TSQQ,3479
+export/scripts/export_onnx.py,sha256=85P2hrU1_eHuibX5iEijwoe2rKduXyKDSk3C6wvFYsM,7278
+export/scripts/onnx_to_savedmodel.py,sha256=OeKddLMuhV39-lx7Cbgh0TZNFNr6JSya1eUTZ4wM9D8,1078
+export/scripts/predict_savedmodel.py,sha256=f-d0VuzXofo1x8JxyQJVzhq1OoNq94pAn117BphQPus,3323
+export/scripts/save_predictions_tf.py,sha256=2QmUo3ElCVD-NNNLLCXDNOuHm5n9RfGMw8T_13V-Oko,17589
+export/scripts/to_tflite.py,sha256=CUiIWhb-FZQyWSwVhbMvQSOPuODL2jRkSNZfyEoWjn0,1002
+export/tests/test_export_onnx_optional.py,sha256=Iuvwpm71ZBqjRC4TVILqYC5K8Q03YCc1DYAdv3rznD4,2458
+export/tests/test_export_wrappers.py,sha256=Dv0UjnNLdvS63Ua-dcgZoEWjuZ3FtPVpHa_GXy-FyUI,3420
+export/tests/test_faster_rcnn_export_parity.py,sha256=rFmBpSWjmhtLrkwELJMBgLdyANvXPLTqAQottbw8YVI,6602
+export/tests/test_ort_runtime.py,sha256=LfANy-OvE3TatfPsnVev7Hl6gMu0mDmaaW2FTtcMD-w,1102
+oriented_det/__init__.py,sha256=4U6f648If8d4QRRfSqI0OxBgZoxYnkwU5vMlMQyYu2s,2462
+oriented_det/cli/__init__.py,sha256=5LGP4TQFKUqp4fcPDyaOuS4cvR2TdpAzzs1wQcog9P8,3497
+oriented_det/cli/train.py,sha256=5Me3LZxU-Hl_xf1xRyYZwJx7fCmx0h-CTvFN9X35Fao,471
+oriented_det/configs/config.schema.json,sha256=C5woB9ukzazc368528H8J_XNUqH2pKhqipl8UUIt6NA,41206
+oriented_det/configs/_base_/augmentation.json,sha256=ELpx8TEDtZcBRPyFYnZ2xJczmWs3JtLUpbH7H3Llcls,355
+oriented_det/configs/_base_/fp16.json,sha256=wNqdxfTeFIk50RVE30XBRhNiYSAHPnawoJ18rvg-VcQ,44
+oriented_det/configs/_base_/preprocessing.json,sha256=NELtNcL_wTPAXwzMI9LMAAhG0XlIHjbolbGU7kmvhSA,161
+oriented_det/configs/_base_/datasets/dota_le90.json,sha256=tMwaZiQtlEkgTKjFTYgXjd6NpaE4NUt5eOZ-c5CURkI,426
+oriented_det/configs/_base_/models/oriented_rcnn_r50.json,sha256=2YvW8O3rJJ1If5PSILij2YmZbURH_dymCArU8MLIYUY,800
+oriented_det/configs/_base_/models/rotated_faster_rcnn_r50.json,sha256=nrwyZYkIPbS5FlADr55rURKGFK0XcdgWWklDKJrJxKQ,1194
+oriented_det/configs/_base_/models/rotated_retinanet_r50.json,sha256=fJg2PAcvgS7r9sxYpgvtvrqK9TxTKdvGjsdS58G3VJY,759
+oriented_det/configs/_base_/schedules/1x.json,sha256=MNwVRKlK17ruJjxqwO1jUqL3YU95gMKeqJuIC2jyiME,754
+oriented_det/configs/oriented_rcnn/dota_le90_1x.json,sha256=HJToX4Cn27_0VDPPd9OiuxZKo5oE-e7YSapVi13viUw,3308
+oriented_det/configs/oriented_rcnn/dota_le90_3x.json,sha256=dYQpUfnhdmeO97sIlaOOwNhiiFSAWZJDz-kN4TcQYAI,188
+oriented_det/configs/rotated_faster_rcnn/dota_le90_1x.json,sha256=fh6-2tbkylpPs_CXnzN6JBnu_XgBwR2ZqwsKNIyP4jw,3270
+oriented_det/configs/rotated_faster_rcnn/dota_le90_3x.json,sha256=O5IE8qVBhDfwwB6h4gpmnEZf8wZHRaZdl9Bu3P5S3vg,182
+oriented_det/configs/rotated_retinanet/dota_le90_1x.json,sha256=jjbNG3qJzikKkhA50GNa5-yhDs6BBm0_Y7acjnzx6Pg,2843
+oriented_det/configs/rotated_retinanet/dota_le90_3x.json,sha256=xacNAkYrEePrFwZ7P43cKaCHcxVnDRwzG_q5C3kBv7E,720
+oriented_det/data/__init__.py,sha256=6BGX-AQ2LqNPmmhlhwD_PSgZQRr28iOaCbEkXJUbR7c,2124
+oriented_det/data/airbus_playground.py,sha256=qVINhAldCCHcxmx0U7zqjeZWx20vcOgfQUyLhv5ZsH4,22398
+oriented_det/data/dota.py,sha256=2WF0zgJg-JBKKR9uz8LVyTP0kOQIzyeSfnx4SUHLmWo,29111
+oriented_det/data/dota_classes.py,sha256=c45xxWp7AIX9DP-RI_NZ4iryo4z8a6nkN17E_-OdObY,643
+oriented_det/data/evaluation.py,sha256=ALs35e94dLrZLc0w_Q2RiqDgEN33ELqoLzEEQ5FiIQk,28877
+oriented_det/data/flips.py,sha256=YFJwyvCagWzE166vxJo-dYn6N1A9hxrRdXjmcF9Ty58,3670
+oriented_det/data/preprocessing.py,sha256=Qkuh2e3NI2fxbGjL1sWSvzLRiu2yc2qYt_1S5kfMFb4,11153
+oriented_det/data/tiling.py,sha256=Sp4UxMqCPybY8oFNKhnaMaEixW_GeJDcwrxOQdhJVRI,13687
+oriented_det/data/transforms.py,sha256=oPdWrUqhC7iukpQrZGUG2b73sUGl_DtHXR0fex3MQtM,14015
+oriented_det/geometry/__init__.py,sha256=rJs3GGihQfctCksBwW-HNaiCoByOnQl1P3iWIAXrWDA,274
+oriented_det/geometry/poly.py,sha256=Y1bkTi6AM_qmI7Ezd1gPhWs8ADnnuLA-IlHF6gZSmSo,4174
+oriented_det/geometry/qbox.py,sha256=evmpz7uFuUPQw3cYVmE5roCzSexRuCp1clk8q1kilSo,1926
+oriented_det/geometry/rbox.py,sha256=EK8l29pW0-6NsTTMjJWFSpoW8pz_EKIWArc5WiB3IpY,8397
+oriented_det/geometry/transforms.py,sha256=T1Ox5kSK3L7pPA4XGUQzPSh4I6hC5gtfykVtVG4mmRI,6976
+oriented_det/models/__init__.py,sha256=FNSQjDYkHC-s5_rahXwA_TjlggtvyAVHnfR0k74gR-M,1011
+oriented_det/models/bbox_coder.py,sha256=qPt3YF15gF1B1MnI_eUdAc1vhxOEcjVMAdAAKUfqtfo,12014
+oriented_det/models/faster_rcnn_inference.py,sha256=WIzW5-xKlotNSOtODvUV0KoNS44Gbo-OAfweNhrb0jo,18422
+oriented_det/models/horizontal_roi_coder.py,sha256=aF6C8vsDQCU6ap4bBRy_HS72in8mH3wbFLVgfP0JPII,5507
+oriented_det/models/oriented_rcnn.py,sha256=7CmHlR_dAwXd8QkOr4rMn86hJQskLO8IlWP0pxlnrpk,67210
+oriented_det/models/oriented_roi.py,sha256=j8vcWIav59b781NVmhTLfnfuv08fi1UcHhs66ujmquU,71016
+oriented_det/models/oriented_rpn.py,sha256=ZxDhBbH3DAwyqPhfzxmeYWjtVvpUqkbLNNXF50tksLk,100493
+oriented_det/models/rotated_retinanet.py,sha256=RyYNK_8fchfzL9pkdjf9RKdF_w8465aLVavQIpWSVgE,51376
+oriented_det/models/utils.py,sha256=ZbV6Jtq2X2DiU6hPheKy7BrkIGK6Pqpo_RI4uhwwU3o,23165
+oriented_det/models/backbones/__init__.py,sha256=pelzaP3J61M5jWk_9EIuLmQxMLB71eg4gV8KhRj26es,306
+oriented_det/models/backbones/resnet_fpn.py,sha256=sn7eJJxpBLM4vXEi3Ss5GrqbdqDvWBcLpjjOBD1OaFI,3266
+oriented_det/models/backbones/utils.py,sha256=dFt3U_AOSlHWLnDmB0phyWApjEZxBvh5mz70k5NmMnU,2620
+oriented_det/ops/__init__.py,sha256=3iA7bKH_aHV3CbaLAiAa4VuZ5IZUfTJSn2VdWIVNbVc,1449
+oriented_det/ops/gpu_ops.py,sha256=UpHcsXhhiuC0KUFZNParDAva7aPAO3H48hVSreT99Sw,41540
+oriented_det/ops/iou.py,sha256=gHFhtb-4GFhcTsYCD2K3dJ08HzJM5LlZjCB3LAzckRE,5947
+oriented_det/ops/kfiou.py,sha256=VxzQNL4xKKJE5l-SSFZUXZzlGYHzW8UhIj11-AyP9Zs,9674
+oriented_det/ops/nms.py,sha256=gnGYAvR0JNeYNA3C1X9rZpyH6mASpR6kqE2uawiX1XM,7505
+oriented_det/ops/probiou.py,sha256=s5QMtPio8eOUriTYzYSA5oeObOkxgzZ7mcnHh72oerw,5164
+oriented_det/ops/rotated_ops.py,sha256=traolOPAUF-632fKP_u2R6TJvdST_b4m0_RLJ-RUNzg,4204
+oriented_det/ops/utils.py,sha256=wfgZK6QQImq738NHu0fu83DhJXeai-gn3HfiZUcR3ao,8523
+oriented_det/pretrained/__init__.py,sha256=eiOvmiVL5CJs7utmc8Uu_Y9VygNU3DMPAYduPWrCAlA,480
+oriented_det/pretrained/hub.py,sha256=ho3kHGOIfPnBy8u7z0f-hhG_-Bulu8xXifEjiTSsCYM,8133
+oriented_det/pretrained/manifest.json,sha256=aJ6hwajF9sqZhiEJLAaIW0Co8mgBrlFFkcMoSMOsk10,2360
+oriented_det/runtime/__init__.py,sha256=nXje0BlmYYoaZB65tDMS9L5451Wq_H8drud6Yj6cx_Y,652
+oriented_det/runtime/checkpoint.py,sha256=XagDEJK1qM3bshDYhU-tVy434Qm4otNbnxOW7Eyl0ik,15427
+oriented_det/runtime/collate.py,sha256=2eCGTtoMBBBaIWfEMDenI17t8CAfKofTm4P3fnB1rbA,14679
+oriented_det/runtime/inference.py,sha256=mMxidc9jLm0wIQVefidl3vxd6M5xSoEFNDfnbUlCgAQ,48905
+oriented_det/train/__init__.py,sha256=qfj2It-nW8OiH0dZAdmliSe824EMlBEHsGNb9uzlUKY,2661
+oriented_det/train/config.py,sha256=0CCs_RACt5RVn8u6C_c_CrbPXZ3SQpQMqNOxyKHmLlc,41844
+oriented_det/train/engine.py,sha256=gV3OoRZR0ENtlnsMLo9uZOJw95a4XCaLMr6--08ohas,141572
+oriented_det/train/grouped_ce.py,sha256=0lbJUTZcm57Njg1teU3Ww0pdGs_XTF3JnpFTAF19mYY,5022
+oriented_det/train/piecewise_schedule.py,sha256=SAxMvo1Bv5UvFugJCThQ2rEqDxO4OAAAFFa6SeENuRY,1038
+oriented_det/train/profiler.py,sha256=7Em9VQSqy534T3zJ-W7QJVo7T4QUxTdOZg_r_-ryo-8,9187
+oriented_det/train/utils.py,sha256=VJhXEsDVIFhia2k_e6_S2RoN3b17CBqjTqlWQpoA89U,41030
+oriented_det/utils/__init__.py,sha256=_dVKwmq7OUcmE9ChyWO8M9rC6hpAGdv3WC0OTwawSeU,693
+oriented_det/utils/config.py,sha256=J8FEB01Vr1N8gGOG-ZKG0PWbuYJ2Hc2NiGfS50z512c,12367
+oriented_det/utils/device.py,sha256=1d_JTdGb2TBySDYiKTvShhwjO-U8TzpEZio0HucVnRA,1285
+oriented_det/utils/logging.py,sha256=Bn2AKLzNyXKagFf6TwU79sUI7kMstbUZcej5jK0eomc,5037
+oriented_det/utils/progress.py,sha256=QUck27RMxzH_BBLjTmnuy2nlcGwD4D7SJrHJpNUc_Io,2144
+oriented_det/utils/viz.py,sha256=yqWXxqBIZuDJaRdVLA4BWwkxvW3DZKQH73AUGl2tyoE,6008
+oriented_det-0.1.0.dist-info/licenses/LICENSE,sha256=zWrwvHYHK37sq-iBd74vqxl6JwGxaaYrgFuV-3yuX74,11371
+tools/__init__.py,sha256=g0EGO5OnTpFAUtBoSs9mHGzgHte_jxYygBQhVJNYKwk,79
+tools/app.py,sha256=BLjNL4F2pFCSQENNMRWPrJPnAyD2E_lb0wizknXWMUg,54023
+tools/dataset_stats.py,sha256=nn_HFr1KaZ1z9LjZdEeS30LXxn09tQH4QoIvESxi4Og,15773
+tools/dota_labels_to_comma.py,sha256=b8Ku3_n2AbYAEdzcRNIu9G7GSqsyZlyig-nAyyidJRs,4663
+tools/free_gpu.py,sha256=E6tM9K7WNdrQkzTcPZSNS3OIP1y4mGQlr9gQtuoDiMk,4318
+tools/generate_airbus_playground_csv.py,sha256=4KoSnt3mqVdVkgVgnnJ_4dvFfDeuvntHnw7soRENong,5393
+tools/image_demo.py,sha256=KqAloSSr84fwPg5a7SasMK8ttONuYaVeih_PASsh9UA,7238
+tools/lr_finder.py,sha256=yNYgHqFnePJE30t1fwjq0qARKzDhBBZUM6Z6PamGfJs,29259
+tools/measure_sampled_riou_error.py,sha256=VLV4hBsAPsvsG0bZdw_JL2qaDVS0XDd3ILIfdXn8HfQ,15334
+tools/playground_to_dota.py,sha256=8x1tq1PgHe1ZD35JGAuXQNKl3tJqNxX7ac3REUKwJv8,11109
+tools/pretrained_download.py,sha256=6V9xG5vAQw9nJvReyKmkWSriPViOwWQ2ie8SB9Q8jFw,1447
+tools/preview_augmentation.py,sha256=97t41BwGP1H6K4VS-rjo__OLvk1XIkrjOa0OHyrEBFg,17361
+tools/publish_checkpoint.py,sha256=TJvyc8EMnWaIBYMFE0JlEZyFHgnuW_BiNQFhH0K-Kw4,3025
+tools/save_predictions.py,sha256=3SQuLxLoNVyHLYeqtVxdIb8GbAZYfYLk4Vghfp2WVLs,105316
+tools/sync_vendored_configs.py,sha256=W_zwvKuLqOOsO1ZleL_Y9BQk5atTdKt5-OMY2vhJguY,2906
+tools/tile_dota.py,sha256=kIzypIa36iUID8k_nUTYgg0KRvDAfrm-SpnatM3MQQ8,16737
+tools/train.py,sha256=hhjLM1slqn_tOwxU4OLGiOgrU5YM1ympzHbDTMYD5H0,109037
+tools/train_example.py,sha256=TT4kIy84D291erJxSh-Vi_EUidP06w27B9-U2yLLcYo,8841
+tools/train_multi_gpu.py,sha256=rWhqzmz4r_6iduoIe4nGFMWTYAewOEcQM_bGlnhyW-I,15029
+tools/visualize_boxes.py,sha256=888tmG2lst1Ijm-sFf2guw-QOFUylKf1iZ1u_0ECq54,6060
+oriented_det-0.1.0.dist-info/METADATA,sha256=enSXiqyZC8VbzIeR9cFeBCrZx8pSBKKl9vbU_cr4hBs,16194
+oriented_det-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+oriented_det-0.1.0.dist-info/entry_points.txt,sha256=KL0zwJ__y-IOna-3pA-bl5KZ6SRtrml78gNsDG762kQ,47
+oriented_det-0.1.0.dist-info/top_level.txt,sha256=Ps78oOIJm0VxN9OeyRHCZ4wrb1Z3rSW392ybT6Up0kQ,26
+oriented_det-0.1.0.dist-info/RECORD,,

oriented_det-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

oriented_det-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+odet = oriented_det.cli:main