temporary commit

.gitignore

@@ -0,0 +1,219 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.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
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.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/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# VS Code
+.vscode/

app.py

@@ -1,6 +1,34 @@
 import evaluate
-from evaluate.utils import launch_gradio_widget
+import gradio as gr
 
 
-module = evaluate.load("sunhill/clip_score")
-launch_gradio_widget(module)
+metric = evaluate.load("clip_score.py")
+
+
+def compute_clip_score(image, text):
+    results = metric.compute(predictions=[text], images=[image])
+    return results["clip_score"]
+
+
+iface = gr.Interface(
+    fn=compute_clip_score,
+    inputs=[
+        gr.Image(type="pil"),
+        gr.Textbox(lines=2, placeholder="Enter text here..."),
+    ],
+    outputs=gr.Number(label="CLIP Score"),
+    title="CLIP Score Evaluator",
+    description="Evaluate the alignment between an image and a text using CLIP Score.",
+    examples=[
+        [
+            "https://images.unsplash.com/photo-1720539222585-346e73f01536",
+            "A cat sitting on a couch.",
+        ],
+        [
+            "https://images.unsplash.com/photo-1694253987647-4eebcf679974",
+            "A scenic view of mountains during sunset.",
+        ],
+    ],
+)
+
+iface.launch()

clip_score.py

@@ -1,68 +1,58 @@
-# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-"""TODO: Add a description here."""
+"""This module calculates CLIPScore, a reference-free evaluation metric for image captioning."""
 
 import evaluate
 import datasets
+from evaluate.utils.logging import get_logger
+from transformers import CLIPProcessor, CLIPModel, AutoTokenizer
 
+logger = get_logger(__name__)
 
-# TODO: Add BibTeX citation
 _CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
+@article{DBLP:journals/corr/abs-2104-08718,
+    author       = {Jack Hessel and
+                    Ari Holtzman and
+                    Maxwell Forbes and
+                    Ronan Le Bras and
+                    Yejin Choi},
+    title        = {CLIPScore: {A} Reference-free Evaluation Metric for Image Captioning},
+    journal      = {CoRR},
+    volume       = {abs/2104.08718},
+    year         = {2021},
+    url          = {https://arxiv.org/abs/2104.08718},
+    eprinttype   = {arXiv},
+    eprint       = {2104.08718},
+    timestamp    = {Sat, 29 Apr 2023 10:09:27 +0200},
+    biburl       = {https://dblp.org/rec/journals/corr/abs-2104-08718.bib},
+    bibsource    = {dblp computer science bibliography, https://dblp.org}
 }
 """
 
-# TODO: Add description of the module here
 _DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
+This new module is designed to calculate CLIPScore, a reference-free evaluation metric for image captioning.
 """
 
 
-# TODO: Add description of the arguments of the module here
 _KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
+Computes CLIPScore to evaluate the alignment between an image and a text.
 Args:
-    predictions: list of predictions to score. Each predictions
-        should be a string with tokens separated by spaces.
-    references: list of reference for each prediction. Each
-        reference should be a string with tokens separated by spaces.
+    predictions: list of text predictions to score. Each prediction
+        should be a string.
+    images: list of images to score against. Each image should be a PIL image.
 Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
+    clip_score: CLIPScore between the image and the text.
 Examples:
-    Examples should be written in doctest format, and should illustrate how
-    to use the function.
-
-    >>> my_new_module = evaluate.load("my_new_module")
-    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
+    >>> metric = evaluate.load("sunhill/clip_score")
+    >>> results = metric.compute(predictions=["A cat sitting on a couch."], images=[PIL_image])
     >>> print(results)
-    {'accuracy': 1.0}
+    {'clip_score': 0.2076}
 """
 
-# TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
-
 
 @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
 class CLIPScore(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
+    """CLIPScore metric."""
 
     def _info(self):
-        # TODO: Specifies the evaluate.EvaluationModuleInfo object
         return evaluate.MetricInfo(
             # This is the description that will appear on the modules page.
             module_type="metric",
@@ -70,26 +60,39 @@ class CLIPScore(evaluate.Metric):
             citation=_CITATION,
             inputs_description=_KWARGS_DESCRIPTION,
             # This defines the format of each prediction and reference
-            features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
-            }),
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Value("string"),
+                    "references": datasets.Value("float32"),
+                }
+            ),
             # Homepage of the module for documentation
-            homepage="http://module.homepage",
+            homepage="https://huggingface.co/spaces/sunhill/clip_score",
             # Additional links to the codebase or references
-            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
-            reference_urls=["http://path.to.reference.url/new_module"]
+            codebase_urls=["https://github.com/Taited/clip-score"],
+            reference_urls=["https://arxiv.org/abs/2104.08718"],
         )
 
     def _download_and_prepare(self, dl_manager):
         """Optional: download external resources useful to compute the scores"""
-        # TODO: Download external resources if needed
-        pass
+        logger.info("Downloading and preparing CLIP ViT-B/32 model...")
+        self.model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+        self.processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+        self.tokenizer = AutoTokenizer.from_pretrained("openai/clip-vit-base-patch32")
 
     def _compute(self, predictions, references):
         """Returns the scores"""
-        # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
-        return {
-            "accuracy": accuracy,
-        }
+        refer = self.processor(
+            text=None, images=references, return_tensors="pt", padding=True
+        )
+        refer["pixel_values"] = refer["pixel_values"][0]
+        pred = self.tokenizer(predictions, return_tensors="pt", padding=True)
+        for key in pred:
+            pred[key] = pred[key].squeeze()
+
+        refer_features = self.model.get_image_features(**refer)
+        pred_features = self.model.get_text_features(**pred)
+
+        refer_features = refer_features / refer_features.norm(dim=1, keepdim=True)
+        pred_features = pred_features / pred_features.norm(dim=1, keepdim=True)
+        return {"clip_score": (refer_features * pred_features).sum().item()}

requirements.txt

@@ -1 +1,2 @@
-git+https://github.com/huggingface/evaluate@main
+git+https://github.com/huggingface/evaluate@main
+transformers