Code Quality Improvements and Development Infrastructure Updates

.dockerignore

@@ -13,4 +13,4 @@ docker-compose.yml
 build/*
 dist/*
 docs/*
-docker/
+docker/

.github/workflows/gpu.yml

@@ -0,0 +1,45 @@
+name: GPU Tests
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  gpu-test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python 3.7
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.7'
+
+    - name: Install FFMPEG
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y ffmpeg
+
+    - name: Install PySide2
+      run: |
+        python -m pip install --upgrade pip
+        pip install "pyside2==5.13.2"
+
+    - name: Install PyTorch with CUDA
+      run: |
+        pip install torch torchvision --index-url https://download.pytorch.org/whl/cu102
+
+    - name: Install package and test dependencies
+      run: |
+        pip install -r requirements.txt
+        pip install pytest pytest-cov
+        python setup.py develop
+
+    - name: GPU Tests
+      run: |
+        pytest -v -m "gpu" tests/
+      env:
+        CUDA_VISIBLE_DEVICES: 0

.github/workflows/main.yml

@@ -0,0 +1,59 @@
+name: CPU Tests
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  test:
+    name: Test on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python 3.7
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.7'
+
+    - name: Install FFMPEG (Ubuntu)
+      if: matrix.os == 'ubuntu-latest'
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y ffmpeg
+
+    - name: Install FFMPEG (macOS)
+      if: matrix.os == 'macos-latest'
+      run: |
+        brew install ffmpeg
+
+    - name: Install FFMPEG (Windows)
+      if: matrix.os == 'windows-latest'
+      run: |
+        choco install ffmpeg
+
+    - name: Install PySide2
+      run: |
+        python -m pip install --upgrade pip
+        pip install "pyside2==5.13.2"
+
+    - name: Install PyTorch CPU
+      run: |
+        pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
+
+    - name: Install package and test dependencies
+      run: |
+        pip install -r requirements.txt
+        pip install pytest pytest-cov
+        python setup.py develop
+
+    - name: Run CPU tests
+      run: |
+        pytest -v -m "not gpu" tests/

.github/workflows/pre-commit.yml

@@ -0,0 +1,28 @@
+name: Pre-commit
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python 3.7
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.7'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pre-commit ruff
+
+    - name: Run pre-commit
+      run: |
+        pre-commit install
+        pre-commit run --all-files

.gitignore

@@ -152,4 +152,4 @@ venv.bak/
 dmypy.json
 
 # Pyre type checker
-.pyre/
+.pyre/

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.4.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+    -   id: check-ast
+    -   id: check-json
+    -   id: check-merge-conflict
+    -   id: detect-private-key
+
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.1
+    hooks:
+    -   id: ruff
+        args: [--fix]
+    -   id: ruff-format

CODEOWNERS

@@ -0,0 +1 @@
+@jbohnslav

MANIFEST.in

@@ -1,3 +1,3 @@
 include README.md
 include deepethogram/gui/icons/*.png
-recursive-include deepethogram/conf *
+recursive-include deepethogram/conf *

README.md

@@ -2,8 +2,8 @@
 - Written by Jim Bohnslav, except where as noted
 - [email protected]
 
-DeepEthogram is an open-source package for automatically classifying each frame of a video into a set of pre-defined 
-behaviors. Designed for neuroscience research, it could be used in any scenario where you need to detect actions from 
+DeepEthogram is an open-source package for automatically classifying each frame of a video into a set of pre-defined
+behaviors. Designed for neuroscience research, it could be used in any scenario where you need to detect actions from
 each frame of a video.
 
 Example use cases:
@@ -12,56 +12,56 @@ Example use cases:
 * Counting licks from video for appetite measurement
 * Measuring reach onset times for alignment with neural activity
 
-DeepEthogram uses state-of-the-art algorithms for *temporal action detection*. We build on the following previous machine 
+DeepEthogram uses state-of-the-art algorithms for *temporal action detection*. We build on the following previous machine
 learning research into action detection:
 * [Hidden Two-Stream Convolutional Networks for Action Recognition](https://arxiv.org/abs/1704.00389)
 * [Temporal Gaussian Mixture Layer for Videos](https://arxiv.org/abs/1803.06316)
 
 ![deepethogram schematic](docs/images/deepethogram_schematic.png)
 
 ## Installation
-For full installation instructions, see [this readme file](docs/installation.md). 
+For full installation instructions, see [this readme file](docs/installation.md).
 
-In brief: 
-* [Install PyTorch](https://pytorch.org/) 
+In brief:
+* [Install PyTorch](https://pytorch.org/)
 * `pip install deepethogram`
 
 ## Data
-**NEW!** All datasets collected and annotated by the DeepEthogram authors are now available from this DropBox link: 
+**NEW!** All datasets collected and annotated by the DeepEthogram authors are now available from this DropBox link:
 https://www.dropbox.com/sh/3lilfob0sz21och/AABv8o8KhhRQhYCMNu0ilR8wa?dl=0
 
-If you have issues downloading the data, please raise an issue on Github. 
+If you have issues downloading the data, please raise an issue on Github.
 
 ## COLAB
-I've written a Colab notebook that shows how to upload your data and train models. You can also use this if you don't 
-have access to a decent GPU. 
+I've written a Colab notebook that shows how to upload your data and train models. You can also use this if you don't
+have access to a decent GPU.
 
-To use it, please [click this link to the Colab notebook](https://colab.research.google.com/drive/1Nf9FU7FD77wgvbUFc608839v2jPYgDhd?usp=sharing). 
-Then, click `copy to Drive` at the top. You won't be able to save your changes to the notebook as-is. 
+To use it, please [click this link to the Colab notebook](https://colab.research.google.com/drive/1Nf9FU7FD77wgvbUFc608839v2jPYgDhd?usp=sharing).
+Then, click `copy to Drive` at the top. You won't be able to save your changes to the notebook as-is.
 
 
 ## News
 We now support docker! Docker is a way to run `deepethogram` in completely reproducible environments, without interacting
 with other system dependencies. [See docs/Docker for more information](docs/docker.md)
 
 ## Pretrained models
-Rather than start from scratch, we will start with model weights pretrained on the Kinetics700 dataset. Go to 
+Rather than start from scratch, we will start with model weights pretrained on the Kinetics700 dataset. Go to
 To download the pretrained weights, please use [this Google Drive link](https://drive.google.com/file/d/1ntIZVbOG1UAiFVlsAAuKEBEVCVevyets/view?usp=sharing).
-Unzip the files in your `project/models` directory. Make sure that you don't add an extra directory when unzipping! The path should be 
+Unzip the files in your `project/models` directory. Make sure that you don't add an extra directory when unzipping! The path should be
 `your_project/models/pretrained_models/{models 1:6}`, not `your_project/models/pretrained_models/pretrained_models/{models1:6}`.
 
 ## Licensing
 Copyright (c) 2020 - President and Fellows of Harvard College. All rights reserved.
 
-This software is free for academic use. For commercial use, please contact the Harvard Office of Technology 
-Development ([email protected]) with cc to Dr. Chris Harvey. For details, see [license.txt](license.txt). 
+This software is free for academic use. For commercial use, please contact the Harvard Office of Technology
+Development ([email protected]) with cc to Dr. Chris Harvey. For details, see [license.txt](license.txt).
 
 ## Usage
 ### [To use the GUI, click](docs/using_gui.md)
 #### [To use the command line interface, click](docs/using_CLI.md)
 
 ## Dependencies
-The major dependencies for DeepEthogram are as follows: 
+The major dependencies for DeepEthogram are as follows:
 * pytorch, torchvision: all the neural networks, training, and inference pipelines were written in PyTorch
 * pytorch-lightning: for nice model training base classes
 * kornia: for GPU-based image augmentations
@@ -76,32 +76,67 @@ The major dependencies for DeepEthogram are as follows:
 * tqdm: for nice progress bars
 
 ## Hardware requirements
-For GUI usage, we expect that the users will be working on a local workstation with a good NVIDIA graphics card. For training via a cluster, you can use the command line interface. 
+For GUI usage, we expect that the users will be working on a local workstation with a good NVIDIA graphics card. For training via a cluster, you can use the command line interface.
 
 * CPU: 4 cores or more for parallel data loading
 * Hard Drive: SSD at minimum, NVMe drive is better.
-* GPU: DeepEthogram speed is directly related to GPU performance. An NVIDIA GPU is absolutely required, as PyTorch uses 
-CUDA, while AMD does not. 
+* GPU: DeepEthogram speed is directly related to GPU performance. An NVIDIA GPU is absolutely required, as PyTorch uses
+CUDA, while AMD does not.
 The more VRAM you have, the more data you can fit in one batch, which generally increases performance. a
 I'd recommend 6GB VRAM at absolute minimum. 8GB is better, with 10+ GB preferred.
-Recommended GPUs: `RTX 3090`, `RTX 3080`, `Titan RTX`, `2080 Ti`, `2080 super`, `2080`, `1080 Ti`, `2070 super`, `2070` 
-Some older ones might also be fine, like a `1080` or even `1070 Ti`/ `1070`. 
+Recommended GPUs: `RTX 3090`, `RTX 3080`, `Titan RTX`, `2080 Ti`, `2080 super`, `2080`, `1080 Ti`, `2070 super`, `2070`
+Some older ones might also be fine, like a `1080` or even `1070 Ti`/ `1070`.
 
 ## testing
-Test coverage is still low, but in the future we will be expanding our unit tests. 
+Test coverage is still low, but in the future we will be expanding our unit tests.
 
 First, download a copy of [`testing_deepethogram_archive.zip`](https://drive.google.com/file/d/1IFz4ABXppVxyuhYik8j38k9-Fl9kYKHo/view?usp=sharing)
- Make a directory in tests called `DATA`. Unzip this and move it to the `deepethogram/tests/DATA` 
-directory, so that the path is `deepethogram/tests/DATA/testing_deepethogram_archive/{DATA,models,project_config.yaml}`. Then run `pytest tests/` to run. 
-the `zz_commandline` test module will take a few minutes, as it is an end-to-end test that performs model training 
-and inference. Its name reflects the fact that it should come last in testing. 
+Make a directory in tests called `DATA`. Unzip this and move it to the `deepethogram/tests/DATA`
+directory, so that the path is `deepethogram/tests/DATA/testing_deepethogram_archive/{DATA,models,project_config.yaml}`.
+
+To run tests:
+```bash
+# Run all tests except GPU tests (default)
+pytest tests/
+
+# Run only GPU tests (requires NVIDIA GPU)
+pytest -m gpu
+
+# Run all tests including GPU tests
+pytest -m ""
+```
+
+GPU tests are skipped by default as they require significant computational resources and time to complete. These tests perform end-to-end model training and inference.
+
+## Developer Guide
+### Code Style and Pre-commit Hooks
+We use pre-commit hooks to maintain code quality and consistency. The hooks include:
+- Ruff for Python linting and formatting
+- Various file checks (trailing whitespace, YAML validation, etc.)
+
+To set up the development environment:
+
+1. Install the development dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+2. Install pre-commit hooks:
+```bash
+pre-commit install
+```
+
+The hooks will run automatically on every commit. You can also run them manually on all files:
+```bash
+pre-commit run --all-files
+```
 
 ## Changelog
 * 0.1.4: bugfixes for dependencies; added docker
 * 0.1.2/3: fixes for multiclass (not multilabel) training
 * 0.1.1.post1/2: batch prediction
 * 0.1.1.post0: flow generator metric bug fix
 * 0.1.1: bug fixes
-* 0.1: deepethogram beta! See above for details. 
+* 0.1: deepethogram beta! See above for details.
 * 0.0.1.post1: bug fixes and video conversion scripts added
 * 0.0.1: initial version

deepethogram/__init__.py

@@ -7,9 +7,9 @@
 # from deepethogram.sequence.inference import sequence_inference
 import importlib.util
 
-spec = importlib.util.find_spec('hydra')
+spec = importlib.util.find_spec("hydra")
 if spec is not None:
-    raise ValueError('Hydra installation found. Please run pip uninstall hydra-core: {}'.format(spec))
+    raise ValueError("Hydra installation found. Please run pip uninstall hydra-core: {}".format(spec))
 # try:
 #     import hydra
 # except Exception as e:

deepethogram/__main__.py

@@ -6,5 +6,5 @@
 # def main(cfg: DictConfig) -> None:
 #     run(cfg)
 
-if __name__ == '__main__':
-    entry()
+if __name__ == "__main__":
+    entry()