feat: 🎉 implement Python Flask application with `facebook/detr-resnet…

…-50` model for object detection

tagger/.gitignore

@@ -0,0 +1,160 @@
+# 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
+.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/

tagger/.vscode/launch.json

@@ -0,0 +1,25 @@
+{
+  // Use IntelliSense to learn about possible attributes.
+  // Hover to view descriptions of existing attributes.
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "name": "Python: Flask",
+      "type": "python",
+      "request": "launch",
+      "module": "flask",
+      "env": {
+        "FLASK_APP": "app.py",
+        "FLASK_DEBUG": "1"
+      },
+      "args": [
+        "run",
+        "--no-debugger",
+        "--no-reload"
+      ],
+      "jinja": true,
+      "justMyCode": true
+    }
+  ]
+}

tagger/app.py

@@ -0,0 +1,77 @@
+import os
+from http import HTTPStatus
+from threading import Thread
+
+import requests
+import torch
+from dotenv import load_dotenv
+from flask import Flask
+from PIL import Image
+from pocketbase import PocketBase
+from transformers import DetrForObjectDetection, DetrImageProcessor
+
+load_dotenv()
+
+app = Flask(__name__)
+
+client = PocketBase(os.getenv("POCKETBASE_URL"))
+
+processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
+model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
+
+
+def get_auth_token(email, password):
+    url = client.build_url(f"/api/admins/auth-with-password")
+
+    req = requests.post(url, json={"identity": email, "password": password})
+
+    return req.json()["token"]
+
+
+def tag_file(file_id):
+    print(f"Tagging {file_id}")
+
+    try:
+        record_url = client.build_url(f"/api/collections/files/records/{file_id}")
+
+        req = requests.get(record_url)
+        record = req.json()
+
+        url = client.build_url(f"/api/files/files/{file_id}/{record['file']}")
+
+        image = Image.open(requests.get(url, stream=True).raw)
+
+        inputs = processor(images=image, return_tensors="pt")
+        outputs = model(**inputs)
+
+        # convert outputs (bounding boxes and class logits) to COCO API
+        # let's only keep detections with score > 0.9
+        target_sizes = torch.tensor([image.size[::-1]])
+        results = processor.post_process_object_detection(
+            outputs, target_sizes=target_sizes, threshold=0.9
+        )[0]
+
+        labels = {model.config.id2label[label.item()] for label in results["labels"]}
+
+        token = get_auth_token(
+            os.getenv("POCKETBASE_ADMIN_EMAIL"), os.getenv("POCKETBASE_ADMIN_PASSWORD")
+        )
+
+        req = requests.patch(
+            record_url,
+            json={"tagsSuggestions": list(labels)},
+            headers={"Authorization": f"Bearer {token}"},
+        )
+
+        if req.status_code != HTTPStatus.OK:
+            app.logger.warn(record_url, req.status_code, req.text)
+    except BaseException as ex:
+        app.logger.error(ex)
+
+
+@app.route("/files/<file_id>", methods=["POST"])
+def start_tag_file(file_id):
+    thread = Thread(target=tag_file, args=(file_id,))
+    thread.start()
+
+    return {"file": file_id, "model": "facebook/detr-resnet-50"}, 202

tagger/requirements-dev.txt

@@ -0,0 +1 @@
+black==23.3.0

tagger/requirements.txt

@@ -0,0 +1,9 @@
+flask==2.3.2
+numpy==1.24.2
+pillow==9.5.0
+pocketbase==0.8.1
+requests==2.30.0
+timm==0.6.13
+torch==2.0.1
+transformers==4.29.0
+urllib3<2.0