active-vision 0.2.0__tar.gz → 0.4.0__tar.gz

active_vision-0.4.0/.github/workflows/docs.yml

@@ -0,0 +1,44 @@
+name: docs
+on:
+    push:
+        branches:
+            - main
+jobs:
+    deploy:
+        runs-on: ubuntu-latest
+        steps:
+            - uses: actions/checkout@v4
+              with:
+                  fetch-depth: 0
+            - uses: actions/setup-python@v5
+              with:
+                  python-version: "3.12"
+
+            - name: Install dependencies
+              run: |
+                  python -m pip install --upgrade pip
+                  pip install --no-deps ".[docs]"
+                  pip install jupyter ipykernel livereload nbconvert nbformat sphinx watchdog mkdocs \
+                      mkdocs-git-revision-date-plugin mkdocs-git-revision-date-localized-plugin \
+                      "mkdocs-jupyter>=0.24.0" "mkdocs-material>=9.1.3" mkdocs-pdf-export-plugin \
+                      mkdocstrings mkdocstrings-crystal mkdocstrings-python-legacy pygments \
+                      pymdown-extensions mkdocs-mermaid2-plugin ansi2html
+            
+            - name: Generate docs
+              run: |
+                  cp README.md docs/index.md
+
+                  jupyter nbconvert nbs/imagenette/quickstart.ipynb --to markdown --output-dir docs/
+                  sed -i 's/\x1b\[[0-9;]*m//g' docs/quickstart.md
+
+                  jupyter nbconvert nbs/imagenette/preparing_data.ipynb --to markdown --output-dir docs/
+                  sed -i 's/\x1b\[[0-9;]*m//g' docs/preparing_data.md
+
+                  jupyter nbconvert nbs/imagenette/active_learning.ipynb --to markdown --output-dir docs/
+                  sed -i 's/\x1b\[[0-9;]*m//g' docs/active_learning.md
+
+                  jupyter nbconvert nbs/imagenette/train.ipynb --to markdown --output-dir docs/
+                  sed -i 's/\x1b\[[0-9;]*m//g' docs/train.md
+
+            - name: Deploy
+              run: mkdocs gh-deploy --force

active_vision-0.4.0/.github/workflows/pypi.yaml

@@ -0,0 +1,27 @@
+name: pypi
+
+on:
+    release:
+        types: [created]
+
+jobs:
+    deploy:
+        runs-on: ubuntu-latest
+
+        steps:
+            - uses: actions/checkout@v4
+            - name: Set up Python
+              uses: actions/setup-python@v5
+              with:
+                  python-version: "3.x"
+            - name: Install dependencies
+              run: |
+                  python -m pip install --upgrade pip
+                  pip install setuptools wheel twine build
+            - name: Build and publish
+              env:
+                  TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+                  TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+              run: |
+                  python -m build
+                  twine upload dist/*

active_vision-0.4.0/.gitignore

@@ -0,0 +1,186 @@
+# models
+models/
+*.pkl
+*.pth
+*.pkl
+
+# Data
+data/
+*.parquet
+*.csv
+
+private/
+
+.DS_Store
+
+# 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
+
+# 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
+
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+# PyPI configuration file
+.pypirc

active_vision-0.4.0/.python-version

@@ -0,0 +1 @@
+3.12

{active_vision-0.2.0/src/active_vision.egg-info → active_vision-0.4.0}/PKG-INFO

@@ -1,10 +1,11 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: active-vision
-Version: 0.2.0
-Summary: Active learning for edge vision.
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
+Version: 0.4.0
+Summary: Active learning for computer vision.
+Project-URL: Homepage, https://github.com/dnth/active-vision
+Project-URL: Bug Tracker, https://github.com/dnth/active-vision/issues
 License-File: LICENSE
+Requires-Python: >=3.10
 Requires-Dist: accelerate>=1.2.1
 Requires-Dist: datasets>=3.2.0
 Requires-Dist: fastai>=2.7.18
@@ -15,15 +16,59 @@ Requires-Dist: loguru>=0.7.3
 Requires-Dist: seaborn>=0.13.2
 Requires-Dist: timm>=1.0.13
 Requires-Dist: transformers>=4.48.0
-Requires-Dist: xinfer>=0.3.2
+Provides-Extra: dev
+Requires-Dist: black>=22.0; extra == 'dev'
+Requires-Dist: flake8>=4.0; extra == 'dev'
+Requires-Dist: isort>=5.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: ansi2html; extra == 'docs'
+Requires-Dist: ipykernel; extra == 'docs'
+Requires-Dist: jupyter; extra == 'docs'
+Requires-Dist: livereload; extra == 'docs'
+Requires-Dist: mkdocs; extra == 'docs'
+Requires-Dist: mkdocs-git-revision-date-localized-plugin; extra == 'docs'
+Requires-Dist: mkdocs-git-revision-date-plugin; extra == 'docs'
+Requires-Dist: mkdocs-jupyter>=0.24.0; extra == 'docs'
+Requires-Dist: mkdocs-material>=9.1.3; extra == 'docs'
+Requires-Dist: mkdocs-mermaid2-plugin; extra == 'docs'
+Requires-Dist: mkdocs-pdf-export-plugin; extra == 'docs'
+Requires-Dist: mkdocstrings; extra == 'docs'
+Requires-Dist: mkdocstrings-crystal; extra == 'docs'
+Requires-Dist: mkdocstrings-python-legacy; extra == 'docs'
+Requires-Dist: nbconvert; extra == 'docs'
+Requires-Dist: nbformat; extra == 'docs'
+Requires-Dist: pygments; extra == 'docs'
+Requires-Dist: pymdown-extensions; extra == 'docs'
+Requires-Dist: sphinx; extra == 'docs'
+Requires-Dist: watchdog; extra == 'docs'
+Provides-Extra: zero-shot
+Requires-Dist: x-infer>=0.3.2; extra == 'zero-shot'
+Description-Content-Type: text/markdown
 
 [![Python Version](https://img.shields.io/badge/python-3.10%2B-blue?style=for-the-badge&logo=python&logoColor=white)](https://pypi.org/project/active-vision/)
 [![PyPI](https://img.shields.io/pypi/v/active-vision?style=for-the-badge&logo=pypi&logoColor=white)](https://pypi.org/project/active-vision/)
 [![Downloads](https://img.shields.io/pepy/dt/active-vision?style=for-the-badge&logo=pypi&logoColor=white&label=Downloads&color=purple)](https://pypi.org/project/active-vision/)
 [![License](https://img.shields.io/badge/License-Apache%202.0-green.svg?style=for-the-badge&logo=apache&logoColor=white)](https://github.com/dnth/active-vision/blob/main/LICENSE)
 
+[colab_badge]: https://img.shields.io/badge/Open%20In-Colab-blue?style=for-the-badge&logo=google-colab
+[kaggle_badge]: https://img.shields.io/badge/Open%20In-Kaggle-blue?style=for-the-badge&logo=kaggle
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/dnth/active-vision/main/assets/logo.png" alt="active-vision">
+    <br />
+    <br />
+    <a href="https://dnth.github.io/active-vision" target="_blank" rel="noopener noreferrer"><strong>Explore the docs »</strong></a>
+    <br />
+    <a href="#️-quickstart" target="_blank" rel="noopener noreferrer">Quickstart</a>
+    ·
+    <a href="https://github.com/dnth/active-vision/issues/new?assignees=&labels=Feature+Request&projects=&template=feature_request.md" target="_blank" rel="noopener noreferrer">Feature Request</a>
+    ·
+    <a href="https://github.com/dnth/active-vision/issues/new?assignees=&labels=bug&projects=&template=bug_report.md" target="_blank" rel="noopener noreferrer">Report Bug</a>
+    ·
+    <a href="https://github.com/dnth/active-vision/discussions" target="_blank" rel="noopener noreferrer">Discussions</a>
+    ·
+    <a href="https://dicksonneoh.com/" target="_blank" rel="noopener noreferrer">About</a>
 </p>
 
 The goal of this project is to create a framework for the active learning loop for computer vision. The diagram below shows a general workflow of how the active learning loop works.
@@ -53,7 +98,8 @@ Uncertainty Sampling:
 
 Diverse Sampling:
 - [X] Random sampling
-- [ ] Model-based outlier
+- [X] Model-based outlier
+- [ ] Embeddings-based outlier
 - [ ] Cluster-based
 - [ ] Representative
 
@@ -88,41 +134,51 @@ pip install -e .
 > uv pip install active-vision
 > ```
 
-## 🛠️ Usage
-See the [notebook](./nbs/04_relabel_loop.ipynb) for a complete example.
-
-Be sure to prepared 3 subsets of the dataset:
-- [Initial samples](./nbs/initial_samples.parquet): A dataframe of a labeled images to train an initial model. If you don't have any labeled data, you can label some images yourself.
-- [Unlabeled samples](./nbs/unlabeled_samples.parquet): A dataframe of *unlabeled* images. We will continuously sample from this set using active learning strategies.
-- [Evaluation samples](./nbs/evaluation_samples.parquet): A dataframe of *labeled* images. We will use this set to evaluate the performance of the model. This is the test set, DO NOT use it for active learning. Split this out in the beginning.
+## 🚀 Quickstart
 
-As a toy example I created the above 3 datasets from the imagenette dataset.
+[![Open In Colab][colab_badge]](https://colab.research.google.com/github/dnth/active-vision/blob/main/nbs/imagenette/quickstart.ipynb)
+[![Open In Kaggle][kaggle_badge]](https://kaggle.com/kernels/welcome?src=https://github.com/dnth/active-vision/blob/main/nbs/imagenette/quickstart.ipynb)
 
 ```python
 from active_vision import ActiveLearner
-import pandas as pd
 
-# Create an active learner instance with a model
-al = ActiveLearner("resnet18")
+# Create an active learner instance
+al = ActiveLearner(name="cycle-1")
+
+# Load model
+al.load_model(model="resnet18", pretrained=True)
 
 # Load dataset 
 train_df = pd.read_parquet("training_samples.parquet")
-al.load_dataset(df, filepath_col="filepath", label_col="label")
+al.load_dataset(train_df, filepath_col="filepath", label_col="label", batch_size=8)
 
 # Train model
-al.train(epochs=3, lr=1e-3)
+al.train(epochs=10, lr=5e-3, head_tuning_epochs=3)
 
 # Evaluate the model on a *labeled* evaluation set
 accuracy = al.evaluate(eval_df, filepath_col="filepath", label_col="label")
 
+# Get summary of the active learning cycle
+al.summary()
+
 # Get predictions from an *unlabeled* set
 pred_df = al.predict(filepaths)
 
-# Sample low confidence predictions from unlabeled set
-uncertain_df = al.sample_uncertain(pred_df, num_samples=10)
+# Sample images using a combination of active learning strategies
+samples = al.sample_combination(
+    pred_df,
+    num_samples=50,
+    combination={
+        "least-confidence": 0.4,
+        "ratio-of-confidence": 0.2,
+        "entropy": 0.2,
+        "model-based-outlier": 0.1,
+        "random": 0.1,
+    },
+)
 
 # Launch a Gradio UI to label the low confidence samples, save the labeled samples to a file
-al.label(uncertain_df, output_filename="uncertain")
+al.label(samples, output_filename="combination.parquet")
 ```
 
 ![Gradio UI](https://raw.githubusercontent.com/dnth/active-vision/main/assets/labeling_ui.png)
@@ -135,8 +191,8 @@ Once complete, the labeled samples will be save into a new df.
 We can now add the newly labeled data to the training set.
 
 ```python
-# Add newly labeled data to training set and save as a new file active_labeled
-al.add_to_train_set(labeled_df, output_filename="active_labeled")
+# Add newly labeled data to the dataset
+al.add_to_dataset(labeled_df, output_filename="active_labeled.parquet")
 ```
 
 Repeat the process until the model is good enough. Use the dataset to train a larger model and deploy.

active_vision-0.2.0/PKG-INFO → active_vision-0.4.0/README.md

@@ -1,29 +1,26 @@
-Metadata-Version: 2.2
-Name: active-vision
-Version: 0.2.0
-Summary: Active learning for edge vision.
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: accelerate>=1.2.1
-Requires-Dist: datasets>=3.2.0
-Requires-Dist: fastai>=2.7.18
-Requires-Dist: gradio>=5.12.0
-Requires-Dist: ipykernel>=6.29.5
-Requires-Dist: ipywidgets>=8.1.5
-Requires-Dist: loguru>=0.7.3
-Requires-Dist: seaborn>=0.13.2
-Requires-Dist: timm>=1.0.13
-Requires-Dist: transformers>=4.48.0
-Requires-Dist: xinfer>=0.3.2
-
 [![Python Version](https://img.shields.io/badge/python-3.10%2B-blue?style=for-the-badge&logo=python&logoColor=white)](https://pypi.org/project/active-vision/)
 [![PyPI](https://img.shields.io/pypi/v/active-vision?style=for-the-badge&logo=pypi&logoColor=white)](https://pypi.org/project/active-vision/)
 [![Downloads](https://img.shields.io/pepy/dt/active-vision?style=for-the-badge&logo=pypi&logoColor=white&label=Downloads&color=purple)](https://pypi.org/project/active-vision/)
 [![License](https://img.shields.io/badge/License-Apache%202.0-green.svg?style=for-the-badge&logo=apache&logoColor=white)](https://github.com/dnth/active-vision/blob/main/LICENSE)
 
+[colab_badge]: https://img.shields.io/badge/Open%20In-Colab-blue?style=for-the-badge&logo=google-colab
+[kaggle_badge]: https://img.shields.io/badge/Open%20In-Kaggle-blue?style=for-the-badge&logo=kaggle
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/dnth/active-vision/main/assets/logo.png" alt="active-vision">
+    <br />
+    <br />
+    <a href="https://dnth.github.io/active-vision" target="_blank" rel="noopener noreferrer"><strong>Explore the docs »</strong></a>
+    <br />
+    <a href="#️-quickstart" target="_blank" rel="noopener noreferrer">Quickstart</a>
+    ·
+    <a href="https://github.com/dnth/active-vision/issues/new?assignees=&labels=Feature+Request&projects=&template=feature_request.md" target="_blank" rel="noopener noreferrer">Feature Request</a>
+    ·
+    <a href="https://github.com/dnth/active-vision/issues/new?assignees=&labels=bug&projects=&template=bug_report.md" target="_blank" rel="noopener noreferrer">Report Bug</a>
+    ·
+    <a href="https://github.com/dnth/active-vision/discussions" target="_blank" rel="noopener noreferrer">Discussions</a>
+    ·
+    <a href="https://dicksonneoh.com/" target="_blank" rel="noopener noreferrer">About</a>
 </p>
 
 The goal of this project is to create a framework for the active learning loop for computer vision. The diagram below shows a general workflow of how the active learning loop works.
@@ -53,7 +50,8 @@ Uncertainty Sampling:
 
 Diverse Sampling:
 - [X] Random sampling
-- [ ] Model-based outlier
+- [X] Model-based outlier
+- [ ] Embeddings-based outlier
 - [ ] Cluster-based
 - [ ] Representative
 
@@ -88,41 +86,51 @@ pip install -e .
 > uv pip install active-vision
 > ```
 
-## 🛠️ Usage
-See the [notebook](./nbs/04_relabel_loop.ipynb) for a complete example.
-
-Be sure to prepared 3 subsets of the dataset:
-- [Initial samples](./nbs/initial_samples.parquet): A dataframe of a labeled images to train an initial model. If you don't have any labeled data, you can label some images yourself.
-- [Unlabeled samples](./nbs/unlabeled_samples.parquet): A dataframe of *unlabeled* images. We will continuously sample from this set using active learning strategies.
-- [Evaluation samples](./nbs/evaluation_samples.parquet): A dataframe of *labeled* images. We will use this set to evaluate the performance of the model. This is the test set, DO NOT use it for active learning. Split this out in the beginning.
+## 🚀 Quickstart
 
-As a toy example I created the above 3 datasets from the imagenette dataset.
+[![Open In Colab][colab_badge]](https://colab.research.google.com/github/dnth/active-vision/blob/main/nbs/imagenette/quickstart.ipynb)
+[![Open In Kaggle][kaggle_badge]](https://kaggle.com/kernels/welcome?src=https://github.com/dnth/active-vision/blob/main/nbs/imagenette/quickstart.ipynb)
 
 ```python
 from active_vision import ActiveLearner
-import pandas as pd
 
-# Create an active learner instance with a model
-al = ActiveLearner("resnet18")
+# Create an active learner instance
+al = ActiveLearner(name="cycle-1")
+
+# Load model
+al.load_model(model="resnet18", pretrained=True)
 
 # Load dataset 
 train_df = pd.read_parquet("training_samples.parquet")
-al.load_dataset(df, filepath_col="filepath", label_col="label")
+al.load_dataset(train_df, filepath_col="filepath", label_col="label", batch_size=8)
 
 # Train model
-al.train(epochs=3, lr=1e-3)
+al.train(epochs=10, lr=5e-3, head_tuning_epochs=3)
 
 # Evaluate the model on a *labeled* evaluation set
 accuracy = al.evaluate(eval_df, filepath_col="filepath", label_col="label")
 
+# Get summary of the active learning cycle
+al.summary()
+
 # Get predictions from an *unlabeled* set
 pred_df = al.predict(filepaths)
 
-# Sample low confidence predictions from unlabeled set
-uncertain_df = al.sample_uncertain(pred_df, num_samples=10)
+# Sample images using a combination of active learning strategies
+samples = al.sample_combination(
+    pred_df,
+    num_samples=50,
+    combination={
+        "least-confidence": 0.4,
+        "ratio-of-confidence": 0.2,
+        "entropy": 0.2,
+        "model-based-outlier": 0.1,
+        "random": 0.1,
+    },
+)
 
 # Launch a Gradio UI to label the low confidence samples, save the labeled samples to a file
-al.label(uncertain_df, output_filename="uncertain")
+al.label(samples, output_filename="combination.parquet")
 ```
 
 ![Gradio UI](https://raw.githubusercontent.com/dnth/active-vision/main/assets/labeling_ui.png)
@@ -135,8 +143,8 @@ Once complete, the labeled samples will be save into a new df.
 We can now add the newly labeled data to the training set.
 
 ```python
-# Add newly labeled data to training set and save as a new file active_labeled
-al.add_to_train_set(labeled_df, output_filename="active_labeled")
+# Add newly labeled data to the dataset
+al.add_to_dataset(labeled_df, output_filename="active_labeled.parquet")
 ```
 
 Repeat the process until the model is good enough. Use the dataset to train a larger model and deploy.