Add initial version of app

.gitignore

@@ -0,0 +1,373 @@
+.gradio
+*.pth
+*.csv
+
+# Created by https://www.toptal.com/developers/gitignore/api/macos,dotenv,python,windows,intellij,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=macos,dotenv,python,windows,intellij,visualstudiocode
+
+### dotenv ###
+.env
+
+### Intellij ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### Intellij Patch ###
+# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
+
+# *.iml
+# modules.xml
+# .idea/misc.xml
+# *.ipr
+
+# Sonarlint plugin
+# https://plugins.jetbrains.com/plugin/7973-sonarlint
+.idea/**/sonarlint/
+
+# SonarQube Plugin
+# https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin
+.idea/**/sonarIssues.xml
+
+# Markdown Navigator plugin
+# https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced
+.idea/**/markdown-navigator.xml
+.idea/**/markdown-navigator-enh.xml
+.idea/**/markdown-navigator/
+
+# Cache file creation bug
+# See https://youtrack.jetbrains.com/issue/JBR-2257
+.idea/$CACHE_FILE$
+
+# CodeStream plugin
+# https://plugins.jetbrains.com/plugin/12206-codestream
+.idea/codestream.xml
+
+# Azure Toolkit for IntelliJ plugin
+# https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij
+.idea/**/azureSettings.xml
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.toptal.com/developers/gitignore/api/macos,dotenv,python,windows,intellij,visualstudiocode

.python-version

@@ -0,0 +1 @@
+3.10

README.md

@@ -1,10 +1,11 @@
 ---
 title: RF-DETR SAHI
 emoji: ⚡
-colorFrom: red
-colorTo: green
+colorFrom: indigo
+colorTo: gray
 sdk: gradio
 sdk_version: 5.35.0
+python_version: 3.10
 app_file: app.py
 pinned: false
 license: apache-2.0

app.py

@@ -0,0 +1,252 @@
+from pathlib import Path
+from typing import Any
+
+import gradio as gr
+import PIL
+from rfdetr import RFDETRBase, RFDETRLarge
+from rfdetr.detr import RFDETR
+from rfdetr.util.coco_classes import COCO_CLASSES
+from sahi import AutoDetectionModel
+from sahi.predict import get_prediction, get_sliced_prediction
+from sahi.utils.file import download_from_url
+
+OUT_DIR = Path(__file__).parent / "out"
+OUT_DIR.mkdir(parents=True, exist_ok=True)
+
+
+MARKDOWN = """
+# RF-DETR + SAHI 🔥
+
+This demo shows how to use [RF-DETR](https://github.com/roboflow/rf-detr) ([Apache-2.0](https://github.com/roboflow/rf-detr/blob/develop/LICENSE)) with [SAHI](https://github.com/obss/sahi) ([MIT](https://github.com/obss/sahi/blob/main/LICENSE)) to run predictions on large images.
+"""
+
+IMAGE_PROCESSING_EXAMPLES = [
+    [
+        "https://raw.githubusercontent.com/obss/sahi/main/demo/demo_data/small-vehicles1.jpeg",
+        "large",
+        560,
+        0.8,
+        224,
+        224,
+        0.2,
+        0.2,
+    ],
+]
+
+
+def load_model(checkpoint: str, resolution: int) -> RFDETR:
+    if checkpoint == "base":
+        return RFDETRBase(resolution=resolution)
+    elif checkpoint == "large":
+        return RFDETRLarge(resolution=resolution)
+    raise TypeError("checkpoint must be a base or large")
+
+
+def extend_model(
+    model: Any,
+    confidence_threshold: float,
+    category_mapping: dict,
+):
+    model = AutoDetectionModel.from_pretrained(
+        model_type="roboflow",
+        model=model,
+        confidence_threshold=confidence_threshold,
+        category_mapping=category_mapping,
+        device="cpu",
+    )
+    return model
+
+
+def download_image(
+    image_url: str,
+    download_dir: Path | str | None = None,
+) -> Path:
+    image_filename = image_url.split("/")[-1]
+
+    if not download_dir:
+        download_dir = OUT_DIR
+
+    if isinstance(download_dir, str):
+        download_dir = Path(download_dir)
+
+    download_dir.mkdir(parents=True, exist_ok=True)
+    download_path = Path(download_dir) / image_filename
+    download_path = download_path.resolve()
+
+    download_from_url(image_url, str(download_path))
+
+    return download_path
+
+
+def run_predictions(
+    image_processing_input_image: PIL.Image.Image,
+    image_processing_checkpoint_dropdown: str,
+    image_processing_resolution_slider: int,
+    image_processing_confidence_slider: float,
+    slice_height: int,
+    slice_width: int,
+    overlap_height_ratio: float,
+    overlap_width_ratio: float,
+):
+    image_path = OUT_DIR / "input_image.jpg"
+    image_processing_input_image = image_processing_input_image.convert("RGB")
+    image_processing_input_image.save(str(image_path))
+
+    # Load model:
+    original_model = load_model(
+        checkpoint=image_processing_checkpoint_dropdown,
+        resolution=image_processing_resolution_slider,
+    )
+
+    # Extend model with SAHI:
+    model = extend_model(
+        model=original_model,
+        confidence_threshold=image_processing_confidence_slider,
+        category_mapping=COCO_CLASSES,
+    )
+
+    # Run original model prediction
+    prediction = get_prediction(
+        str(image_path),
+        model,
+    )
+    original_filename = f"{image_path.stem}_prediction"
+    prediction.export_visuals(
+        export_dir=str(OUT_DIR),
+        file_name=original_filename,
+    )
+    original_path = OUT_DIR / f"{original_filename}.png"
+
+    # Run sliced model prediction
+    prediction_sliced = get_sliced_prediction(
+        str(image_path),
+        model,
+        slice_width=slice_width,
+        slice_height=slice_height,
+        overlap_width_ratio=overlap_width_ratio,
+        overlap_height_ratio=overlap_height_ratio,
+        postprocess_match_threshold=image_processing_confidence_slider,
+    )
+    scliced_filename = f"{image_path.stem}_sliced_prediction"
+    prediction_sliced.export_visuals(
+        export_dir=str(OUT_DIR),
+        file_name=scliced_filename,
+    )
+    sliced_path = OUT_DIR / f"{scliced_filename}.png"
+
+    return original_path, sliced_path
+
+
+with gr.Blocks(delete_cache=(10, 10)) as demo:
+    gr.Markdown(MARKDOWN)
+
+    with gr.Row():
+        image_processing_input_image = gr.Image(
+            label="Original Image",
+            image_mode="RGB",
+            type="pil",
+            height=600,
+        )
+        image_processing_output_image = gr.ImageSlider(
+            label="Original vs Sliced Prediction",
+            image_mode="RGB",
+            type="filepath",
+            height=600,
+        )
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### RF-DETR Configuration")
+            image_processing_confidence_slider = gr.Slider(
+                label="Confidence",
+                minimum=0.0,
+                maximum=1.0,
+                step=0.05,
+                value=0.5,
+            )
+            image_processing_resolution_slider = gr.Slider(
+                label="Inference Resolution",
+                minimum=560,
+                maximum=1120,
+                step=56,
+                value=728,
+            )
+            image_processing_checkpoint_dropdown = gr.Dropdown(
+                label="Model Size",
+                choices=["base", "large"],
+                value="base",
+            )
+        with gr.Column():
+            gr.Markdown("### SAHI Configuration")
+            slice_width = gr.Slider(
+                label="Slice Width",
+                minimum=100,
+                maximum=500,
+                step=1,
+                value=224,
+            )
+            slice_height = gr.Slider(
+                label="Slice Height",
+                minimum=100,
+                maximum=500,
+                step=1,
+                value=224,
+            )
+            overlap_width_ratio = gr.Slider(
+                label="Overlap Width Ratio",
+                minimum=0.0,
+                maximum=1.0,
+                step=0.05,
+                value=0.2,
+            )
+            overlap_height_ratio = gr.Slider(
+                label="Overlap Height Ratio",
+                minimum=0.0,
+                maximum=1.0,
+                step=0.05,
+                value=0.2,
+            )
+
+    with gr.Row():
+        with gr.Column():
+            image_processing_submit_button = gr.Button("Submit")
+
+    with gr.Row():
+        gr.Examples(
+            fn=run_predictions,
+            examples=IMAGE_PROCESSING_EXAMPLES,
+            inputs=[
+                image_processing_input_image,
+                image_processing_checkpoint_dropdown,
+                image_processing_resolution_slider,
+                image_processing_confidence_slider,
+                slice_height,
+                slice_width,
+                overlap_height_ratio,
+                overlap_width_ratio,
+            ],
+            outputs=[image_processing_output_image],
+            run_on_click=True,
+            cache_examples=False,
+            cache_mode="eager",
+        )
+
+    image_processing_submit_button.click(
+        fn=run_predictions,
+        inputs=[
+            image_processing_input_image,
+            image_processing_checkpoint_dropdown,
+            image_processing_resolution_slider,
+            image_processing_confidence_slider,
+            slice_height,
+            slice_width,
+            overlap_height_ratio,
+            overlap_width_ratio,
+        ],
+        outputs=[image_processing_output_image],
+    )
+
+
+if __name__ == "__main__":
+    demo.launch(
+        debug=False,
+    )

pyproject.toml

@@ -0,0 +1,9 @@
+[project]
+name = "rf-detr-sahi"
+version = "0.1.0"
+requires-python = ">=3.10"
+dependencies = [
+    "gradio~=5.35.0",
+    "rfdetr~=1.1.0",
+    "sahi~=0.11.26",
+]

requirements.txt

@@ -0,0 +1,3 @@
+gradio~=5.35.0
+rfdetr~=1.1.0
+sahi~=0.11.26