first commit

.gitignore

@@ -0,0 +1,165 @@
+datasets/
+model_records/
+config/
+*.env
+
+# 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/

requirements.txt

@@ -0,0 +1,3 @@
+openai
+opencv-python
+python-dotenv

src/obs_eval.py

@@ -0,0 +1,70 @@
+import cv2
+import base64
+import time
+import openai
+import requests
+import os
+import argparse
+from dotenv import dotenv_values, load_dotenv
+import time
+
+config = dotenv_values("/workspace/Research/PangyoPangyo/src/.env")
+
+openai.organization = config.get('OPENAI_ORGANIZATION')
+openai.api_key = config.get('OPENAI_API_KEY')
+
+def define_argparser():
+    p = argparse.ArgumentParser()
+
+    p.add_argument("--data_path", type=str, required=True)
+    
+    config = p.parse_args()
+
+    return config
+
+
+def main(config):
+    # Ensure the dataset directory exists and has the video file
+    if not os.path.exists(config.data_path):
+        print("Video file not found. Make sure data_path exists.")
+        return
+
+    video = cv2.VideoCapture(config.data_path)
+
+    base64Frames = []
+    while video.isOpened():
+        success, frame = video.read()
+        if not success:
+            break
+        _, buffer = cv2.imencode(".jpg", frame)
+        base64Frames.append(base64.b64encode(buffer).decode("utf-8"))
+
+    video.release()
+    print(len(base64Frames), "frames read.")
+
+    # Skipping the display part as it's not relevant in a .py script
+
+    PROMPT_MESSAGES = [
+        {
+            "role": "user",
+            "content": [
+                "These are frames of a video. Create a short voiceover script in the style of a super excited brazilian sports narrator who is narrating his favorite match. He is a big fan of Messi, the player who scores in this clip. Use caps and exclamation marks where needed to communicate excitement. Only include the narration, your output must be in english. When the ball goes into the net, you must scream GOL either once or multiple times.",
+                *map(lambda x: {"image": x, "resize": 768}, base64Frames[0::10]),
+            ],
+        },
+    ]
+    params = {
+        "model": "gpt-4-vision-preview",
+        "messages": PROMPT_MESSAGES,
+        "api_key": openai.api_key,
+        "headers": {"Openai-Version": "2020-11-07"},
+        "max_tokens": 500,
+    }
+
+    result = openai.ChatCompletion.create(**params)
+    print(result.choices[0].message.content)
+
+
+if __name__ == "__main__":
+    config = define_argparser()
+    main(config)

src/obs_eval.sh

@@ -0,0 +1,5 @@
+
+
+
+python obs_eval.py \
+    --data_path "/workspace/Research/gpt_4_vision_for_eval/datasets/messi2.mp4"