Added clip gradio web interface

.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 +1,106 @@
+import gradio as gr
+from PIL import Image
+from transformers import CLIPProcessor, CLIPModel
+
+sample_images = [f"./sample_images/{i}.jpg" for i in range(5)]
+prediction_image = None
+
+clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+
+def upload_file(files):
+    file_paths = [file.name for file in files]
+    return file_paths
+
+
+def read_image(path):
+    img = Image.open(path)
+    return img
+
+
+def set_prediction_image(evt: gr.SelectData, gallery):
+    global prediction_image
+    if isinstance(gallery[evt.index], dict):
+        prediction_image = gallery[evt.index]["name"]
+    else:
+        prediction_image = gallery[evt.index][0]["name"]
+
+
+def predict(text):
+    text_classes = text.split(",")
+    text_classes = [sentence.strip() for sentence in text_classes]
+
+    image = read_image(prediction_image)
+
+    inputs = clip_processor(
+        text=text_classes,
+        images=image,
+        return_tensors="pt",
+        padding=True,
+    )
+    outputs = clip_model(**inputs)
+    logits_per_image = (
+        outputs.logits_per_image
+    )  # this is the image-text similarity score
+    probs = logits_per_image.softmax(dim=1)[0]
+    results = {text_class: prob.item() for text_class, prob in zip(text_classes, probs)}
+    return {output: gr.update(value=results)}
+
+
+with gr.Blocks() as app:
+    gr.Markdown("## ERA Session19 - Zero Shot Classification with CLIP")
+    gr.Markdown(
+        "Please an image or select one of the sample images. Type some classification labels separated by comma. For ex: dog, cat"
+    )
+    with gr.Row():
+        with gr.Column():
+            with gr.Box():
+                with gr.Group():
+                    upload_gallery = gr.Gallery(
+                        value=None,
+                        label="Uploaded images",
+                        show_label=False,
+                        elem_id="gallery_upload",
+                        columns=5,
+                        rows=2,
+                        height="auto",
+                        object_fit="contain",
+                    )
+                    upload_button = gr.UploadButton(
+                        "Click to Upload images",
+                        file_types=["image"],
+                        file_count="multiple",
+                    )
+                    upload_button.upload(upload_file, upload_button, upload_gallery)
+
+                with gr.Group():
+                    sample_gallery = gr.Gallery(
+                        value=sample_images,
+                        label="Sample images",
+                        show_label=False,
+                        elem_id="gallery_sample",
+                        columns=3,
+                        rows=2,
+                        height="auto",
+                        object_fit="contain",
+                    )
+
+                upload_gallery.select(set_prediction_image, inputs=[upload_gallery])
+                sample_gallery.select(set_prediction_image, inputs=[sample_gallery])
+            with gr.Box():
+                input_text = gr.TextArea(
+                    label="Classification Text",
+                    placeholder="Please enter comma separated text",
+                    interactive=True,
+                )
+
+            submit_btn = gr.Button(value="Submit")
+        with gr.Column():
+            with gr.Box():
+                output = gr.Label(value=None, label="Classification Results")
+
+            submit_btn.click(predict, inputs=[input_text], outputs=[output])
+
+
+app.launch()

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+torchvision
+gradio