Add initial space

.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

@@ -5,6 +5,7 @@ colorFrom: gray
 colorTo: yellow
 sdk: gradio
 sdk_version: 5.46.0
+python_version: 3.10.0
 app_file: app.py
 pinned: false
 license: apache-2.0

app.py

@@ -0,0 +1,192 @@
+import gradio as gr
+import PIL.Image
+import torch
+from transformers import AutoModelForZeroShotObjectDetection, AutoProcessor
+
+# DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+DEVICE = "cpu"
+
+
+class Detector:
+    def __init__(self, model_id: str):
+        self.device = DEVICE
+        self.processor = AutoProcessor.from_pretrained(model_id)
+        self.model = AutoModelForZeroShotObjectDetection.from_pretrained(model_id).to(
+            self.device
+        )
+
+    def detect(
+        self,
+        image: PIL.Image.Image,
+        text_labels: list[str],
+        threshold: float = 0.4,
+    ):
+        inputs = self.processor(
+            images=image, text=[text_labels], return_tensors="pt"
+        ).to(self.device)
+
+        with torch.no_grad():
+            outputs = self.model(**inputs)
+
+        results = self.processor.post_process_grounded_object_detection(
+            outputs, threshold=threshold, target_sizes=[(image.height, image.width)]
+        )
+
+        detections = []
+        result = results[0]
+        for box, score, labels in zip(
+            result["boxes"], result["scores"], result["labels"]
+        ):
+            box = [round(x, 2) for x in box.tolist()]
+            detections.append(
+                dict(
+                    label=labels,
+                    confidence=round(score.item(), 3),
+                    box=box,
+                )
+            )
+        return detections
+
+
+models = dict(
+    tiny=Detector("iSEE-Laboratory/llmdet_tiny"),
+    base=Detector("iSEE-Laboratory/llmdet_base"),
+    large=Detector("iSEE-Laboratory/llmdet_large"),
+)
+
+
+def _postprocess(detections):
+    annotations = []
+    for detection in detections:
+        box = detection["box"]
+        mask = (int(box[0]), int(box[1]), int(box[2]), int(box[3]))
+        label = f"{detection['label']} ({detection['confidence']:.2f})"
+        annotations.append((mask, label))
+    return annotations
+
+
+def detect_objects(image, labels, confidence_threshold):
+    labels = [label.strip() for label in labels.split(",")]
+    return (
+        (
+            image,
+            _postprocess(
+                models["tiny"].detect(
+                    image,
+                    labels,
+                    threshold=confidence_threshold,
+                )
+            ),
+        ),
+        (
+            image,
+            _postprocess(
+                models["base"].detect(
+                    image,
+                    labels,
+                    threshold=confidence_threshold,
+                )
+            ),
+        ),
+        (
+            image,
+            _postprocess(
+                models["large"].detect(
+                    image,
+                    labels,
+                    threshold=confidence_threshold,
+                )
+            ),
+        ),
+    )
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# LLMDet Open Vocabulary Object Detection")
+
+    confidence_slider = gr.Slider(
+        0,
+        1,
+        value=0.4,
+        step=0.01,
+        interactive=True,
+        label="Confidence threshold",
+    )
+
+    labels = [
+        "backpack",
+        "bag",
+        "belt",
+        "blouse",
+        "boot",
+        "bracelet",
+        "cap",
+        "cardigan",
+        "coat",
+        "dress",
+        "earring",
+        "flipflop",
+        "glasses",
+        "glove",
+        "handbag",
+        "hat",
+        "heels",
+        "jacket",
+        "jeans",
+        "loafer",
+        "necklace",
+        "pullover",
+        "raincoat",
+        "ring",
+        "sandal",
+        "scarf",
+        "shirt",
+        "shoe",
+        "shorts",
+        "skirt",
+        "slippers",
+        "sneaker",
+        "socks",
+        "suitcase",
+        "sunglasses",
+        "sweater",
+        "tshirt",
+        "tie",
+        "top",
+        "trouser",
+        "umbrella",
+        "vest",
+        "watch",
+    ]
+
+    # Requested labels
+    text_input = gr.Textbox(
+        label="Object labels (comma separated)!",
+        placeholder="shirt, jeans, shoe",
+        lines=1,
+        value=",".join(labels),
+    )
+
+    with gr.Row():
+        image_input = gr.Image(type="pil", image_mode="RGB")
+
+    with gr.Row():
+        output_annotated_image_tiny = gr.AnnotatedImage(label="TINY")
+        output_annotated_image_base = gr.AnnotatedImage(label="BASE")
+        output_annotated_image_large = gr.AnnotatedImage(label="LARGE")
+
+    detect_button = gr.Button("Detect")
+
+    # Connect the button to the detection function
+    detect_button.click(
+        fn=detect_objects,
+        inputs=[image_input, text_input, confidence_slider],
+        outputs=[
+            output_annotated_image_tiny,
+            output_annotated_image_base,
+            output_annotated_image_large,
+        ],
+    )
+
+if __name__ == "__main__":
+    demo.launch()

pyproject.toml

@@ -0,0 +1,8 @@
+[project]
+name = "llmdet-arena"
+version = "0.1.0"
+requires-python = ">=3.10"
+dependencies = [
+    "gradio~=5.46.0",
+    "transformers[torch]~=4.56.1",
+]

requirements.txt

@@ -0,0 +1,2 @@
+gradio~=5.46.0
+transformers[torch]~=4.56.1