Add app

.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/

app.py

@@ -0,0 +1,63 @@
+import gradio as gr
+from transformers import pipeline
+from PIL import ImageDraw
+import torch
+
+detector = pipeline("zero-shot-object-detection", model="google/owlvit-base-patch32")
+depth_estimator = pipeline("depth-estimation", model="vinvino02/glpn-nyu")
+
+def visualize_preds(image, predictions):
+    new_image = image.copy()
+    draw = ImageDraw.Draw(new_image)
+
+    for prediction in predictions:
+        box = prediction["box"]
+        label = prediction["label"]
+        score = prediction["score"]
+        xmin, ymin, xmax, ymax = box.values()
+        draw.rectangle((xmin, ymin, xmax, ymax), outline="red", width=1)
+        draw.text((xmin, ymin), f"{label}: {round(score,2)}", fill="white")
+
+    return new_image
+
+def compute_depth(image, preds):
+    
+    output = depth_estimator(image)
+    print(output)
+    prediction = torch.nn.functional.interpolate(
+        output["predicted_depth"].unsqueeze(1),
+        size=image.size[::-1],
+        mode="bicubic",
+        align_corners=False,
+    ).squeeze().numpy()
+
+    output = []
+
+    for pred in preds:
+        x = (pred["box"]["xmax"] - pred["box"]["xmin"]) // 2
+        y = (pred["box"]["ymax"] - pred["box"]["ymin"]) // 2
+        output.append({
+            "distance": prediction[x][y]
+        })
+
+    return output
+
+def process(image, text):
+    items = text.split(".")
+    preds = detector(image, candidate_labels=items)
+    return [visualize_preds(image, preds), compute_depth(image, preds)]
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column(scale=1):
+            image = gr.Image(type="pil")
+            name = gr.Textbox(label="Name")
+            greet_btn = gr.Button("Greet")
+        with gr.Column(scale=1):
+            output_detection = gr.Image(type="pil")
+            output_distance = gr.JSON(label="Distance")
+
+
+    greet_btn.click(fn=process, inputs=[image, name], outputs=[output_detection, output_distance], api_name="process")
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers==4.28.1
+gradio==3.28.3
+torch==2.0.0