Updates for 2025 edition

.github/workflows/pre-commit.yml

@@ -14,12 +14,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
-      - name: Set up Python 3.8
-        uses: actions/setup-python@v2
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: 3.12
 
       - name: Install and run pre-commit hooks
-        uses: pre-commit/action@v2.0.0
+        uses: pre-commit/action@v3.0.1

.gitignore

@@ -105,3 +105,7 @@ venv.bak/
 
 # IDEs
 .idea
+
+# Project data
+data.tar.gz
+/data/

.pre-commit-config.yaml

@@ -3,36 +3,43 @@ default_language_version:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v5.0.0
     hooks:
-      - id: check-added-large-files
-        args: [ --maxkb=15000 ]
       - id: trailing-whitespace
       - id: end-of-file-fixer
+      - id: check-docstring-first
       - id: check-yaml
+      - id: debug-statements
+      - id: detect-private-key
+      - id: check-executables-have-shebangs
       - id: check-toml
+      - id: check-case-conflict
+      - id: check-added-large-files
+        args: [ --maxkb=15000 ]
 
-  - repo: https://github.com/timothycrosley/isort
-    rev: 5.12.0
-    hooks:
-      - id: isort
-        types: [ python ]
-
-  - repo: https://github.com/psf/black
-    rev: 23.1.0
-    hooks:
-      - id: black
-        types: [ python ]
-
-  - repo: https://github.com/pycqa/flake8
-    rev: 6.0.0
+  # python linting and code formatting
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.0
     hooks:
-      - id: flake8
-        args: [--config, ./setup.cfg]
-        types: [ python ]
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
 
+  # jupyter notebook cell output clearing
   - repo: https://github.com/kynan/nbstripout
-    rev: 0.6.1
+    rev: 0.8.1
     hooks:
       - id: nbstripout
-        files: '.ipynb'
+
+  # md formatting
+  - repo: https://github.com/hukkin/mdformat
+    rev: 0.7.22
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-gfm
+          - mdformat-frontmatter
+          - mdformat-footnote
+          - mdformat-gfm-alerts
+          - mdformat-tables

README.md

@@ -1,51 +1,69 @@
 # Auto-encoder Tutorials
+
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 ## Setup
 
 ### Virtual Environment
-If you don't operate inside a virtual environment, or only have access to an incompatible python version (<3.8), it is
+
+If you don't operate inside a virtual environment, or only have access to an incompatible python version (\<3.8), it is
 recommended you create a virtual environment using [`conda`](https://docs.conda.io/en/latest/):
+
 ```shell script
 conda env create -f environment.yml
 conda activate deep-learning-tutorials
 ```
+
 Creating the environment this way also takes care of installing the dependencies for you, so you can skip the rest of
 the setup and dive straight into one of the tutorials.
 
 ### Installing Dependencies
+
 If you already have a python environment set aside for this project and just want to install the dependencies, you can
 do that using the following command:
+
 ```shell script
 pip install -e .
 ```
 
-
 ## How to Run
+
 Once you've went through the [setup](#setup) instructions above, you can start exploring the tutorial's notebooks.
 We recommend using JupyterLab to run the notebooks, which can be launched by running (from within your environment):
+
 ```shell script
 jupyter-lab
 ```
+
 When you've launched JupyterLab's web interface, you can simply navigate to any of the
 [tutorials listed below](#available-tutorials), and follow the instructions in there!
 
-
 ## Available Tutorials
 
 ### Representation Learning
+
 - [Basic Variational Autoencoders](tutorials/mnist-autoencoders.ipynb)
 - [Variational Autoencoders Applied to Cardiac MRI](tutorials/cardiac-mri-autoencoders.ipynb)
 
-You may download the MNIST and ACDC datasets [here](https://drive.google.com/file/d/1H5pTOYjcSFR6B5GhA0sEPW0wgPVfBq8S/view?usp=sharing).  Once downloaded, you may untar the file and copy the **data/** folder in the root of your code, at the same level than the **src/** and the **tutorials/** folders.
+The datasets used in this tutorial (MNIST and ACDC) will automatically be downloaded at the beginning of the notebooks.
+However, if you experience issues with the download and want to download the datasets, you can find them [here](https://drive.google.com/file/d/1H5pTOYjcSFR6B5GhA0sEPW0wgPVfBq8S/view?usp=sharing) or download it with the following command:
+
+```shell script
+gdown https://drive.google.com/uc?id=1H5pTOYjcSFR6B5GhA0sEPW0wgPVfBq8S -c -O data.tar.gz
 ```
+
+Once downloaded, you may untar the file and and copy the `data/` folder at the root of the project, i.e. at the same level as the `src/` and the `tutorials/` folders.
+
+```shell script
 tar -xvzf data.tar.gz
 ```
 
 ## How to Contribute
+
 If you want to contribute to the project, then you have to install development dependencies and pre-commit hooks, on
 top of the basic setup for using the project, detailed [above](#setup). The pre-commit hooks are there to ensure that
 any code committed to the repository meets the project's format and quality standards.
+
 ```shell script
 # Install development dependencies
 pip install -e .[dev]

dev.txt

@@ -1,4 +1,2 @@
 pre-commit
-isort
-black
-flake8
+ruff

pyproject.toml

@@ -1,9 +1,5 @@
-[tool.black]
+[tool.ruff]
 line-length = 120
-target-version = ["py38"]
-exclude = "(.eggs|.git|.hg|.mypy_cache|.nox|.tox|.venv|.svn|_build|buck-out|build|dist)"
 
-[tool.isort]
-profile = "black"
-line_length = 120
-src_paths = ["src"]
+[tool.ruff.lint.pydocstyle]
+convention = "google"

requirements.txt

@@ -1,15 +1,15 @@
 # Base requirements
+gdown
+holoviews[recommended]
 jupyterlab
 jupyter
+matplotlib
+numpy
 torch
-torchvision
 torchinfo
+torchvision
 tqdm
-numpy
-matplotlib
-holoviews[recommended]
 umap-learn
 
 # cardiac-mri-autoencoders
 h5py
-torchmetrics

src/data/utils.py

@@ -0,0 +1,42 @@
+from typing import Optional
+
+import torch
+from torch import Tensor
+
+
+def to_onehot(
+    label_tensor: Tensor,
+    num_classes: Optional[int] = None,
+) -> Tensor:
+    """Convert  a dense label tensor to one-hot format.
+
+    References:
+        Copied from `torchmetrics.utilities.data.to_onehot` (v1.6.2, 2025-03-25):
+        https://lightning.ai/docs/torchmetrics/stable/references/utilities.html#to-onehot
+
+    Args:
+        label_tensor: dense label tensor, with shape [N, d1, d2, ...]
+        num_classes: number of classes C
+
+    Returns:
+        A sparse label tensor with shape [N, C, d1, d2, ...]
+
+    Example:
+        >>> x = torch.tensor([1, 2, 3])
+        >>> to_onehot(x)
+        tensor([[0, 1, 0, 0],
+                [0, 0, 1, 0],
+                [0, 0, 0, 1]])
+    """
+    if num_classes is None:
+        num_classes = int(label_tensor.max().detach().item() + 1)
+
+    tensor_onehot = torch.zeros(
+        label_tensor.shape[0],
+        num_classes,
+        *label_tensor.shape[1:],
+        dtype=label_tensor.dtype,
+        device=label_tensor.device,
+    )
+    index = label_tensor.long().unsqueeze(1).expand_as(tensor_onehot)
+    return tensor_onehot.scatter_(1, index, 1.0)