Initial commit

.gitignore

@@ -0,0 +1,162 @@
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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
+.env
+.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/

README.md

@@ -0,0 +1,39 @@
+# Object detection
+
+Aim: AI-driven object detection (on COCO image dataset)
+
+## Direct object detection via python scripts
+
+### 1. Use of torch library
+> python detect_torch.py 
+
+### 2. Use of transformers library
+> python detect_transformers.py
+
+### 3. Use of HuggingFace pipeline library
+> python detect_pipeline.py
+
+## Object detection via User Interface 
+Use of Gradio library for web interface
+
+Command line:
+> python app.py
+
+<b>Note:</b> The Gradio app should now be accessible at http://localhost:7860
+
+## Object detection via Gradio client API
+
+<b>Note:</b> Use of existing Gradio server (running locally, in a Docker container, or in the cloud as a HuggingFace space or AWS)
+
+### 1. Creation of docker container
+
+Command lines:
+> sudo docker build -t gradio-app .
+
+> sudo docker run -p 7860:7860 gradio-app
+
+The Gradio app should now be accessible at http://localhost:7860
+
+### 2. Direct inference via API
+Command line:
+> python inference_API.py

app.py

@@ -0,0 +1,79 @@
+# app.py
+
+import gradio as gr
+#import spaces
+#import torch
+
+from PIL import Image
+from transformers import pipeline
+import matplotlib.pyplot as plt
+import io
+
+model_pipeline = pipeline(model="facebook/detr-resnet-50")
+
+
+COLORS = [
+    [0.000, 0.447, 0.741],
+    [0.850, 0.325, 0.098],
+    [0.929, 0.694, 0.125],
+    [0.494, 0.184, 0.556],
+    [0.466, 0.674, 0.188],
+    [0.301, 0.745, 0.933],
+]
+
+
+def get_output_figure(pil_img, results, threshold):
+    plt.figure(figsize=(16, 10))
+    plt.imshow(pil_img)
+    ax = plt.gca()
+    colors = COLORS * 100
+
+    for result in results:
+        score = result["score"]
+        label = result["label"]
+        box = list(result["box"].values())
+        if score > threshold:
+            c = COLORS[hash(label) % len(COLORS)]
+            ax.add_patch(
+                plt.Rectangle((box[0], box[1]), box[2] - box[0], box[3] - box[1], fill=False, color=c, linewidth=3)
+            )
+            text = f"{label}: {score:0.2f}"
+            ax.text(box[0], box[1], text, fontsize=15, bbox=dict(facecolor="yellow", alpha=0.5))
+    plt.axis("off")
+
+    return plt.gcf()
+
+
+#@spaces.GPU
+def detect(image):
+    results = model_pipeline(image)
+    print(results)
+
+    output_figure = get_output_figure(image, results, threshold=0.9)
+
+    buf = io.BytesIO()
+    output_figure.savefig(buf, bbox_inches="tight")
+    buf.seek(0)
+    output_pil_img = Image.open(buf)
+
+    return output_pil_img
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Object detection with DETR on COCO dataset")
+    gr.Markdown(
+        """
+        This application uses a DETR (DEtection TRansformers) model to detect objects on images.
+        This version was trained using the COCO dataset.
+        You can load an image and see the predictions for the objects detected.
+        """
+    )
+
+    gr.Interface(
+        fn=detect,
+        inputs=gr.Image(label="Input image", type="pil"),
+        outputs=[gr.Image(label="Output prediction", type="pil")],
+        examples=['samples/savanna.jpg'],
+    )
+
+demo.launch(show_error=True)

requirements.txt

@@ -0,0 +1,11 @@
+numpy==1.26.4
+pillow==11.0.0
+torch==2.2.2
+torchvision==0.17.2
+requests==2.32.3
+matplotlib==3.9.2
+scipy==1.14.1
+transformers==4.46.2
+huggingface-hub==0.26.2
+gradio==5.5.0
+timm==1.0.11