Merge branch 'main' into fsd50K_speech_model_finetuning

.azure/ipynb-publish.yml

@@ -93,7 +93,7 @@ jobs:
       COMMIT_HASH: "$(Build.SourceVersion)"
       DEVICES: $( python -c 'print("$(Agent.Name)".split("_")[-1])' )
 
-    condition: ne(dependencies.check_diff.outputs['mtrx.dirs'], '')
+    condition: ne(dependencies.sync_pub.outputs['mtrx.dirs'], '')
 
     steps:
     - bash: |
@@ -129,6 +129,8 @@ jobs:
         git ls-remote --heads origin ${PUB_BRANCH} | grep ${PUB_BRANCH} >/dev/null
         if [ "$?" == "1" ] ; then echo "Branch doesn't exist"; exit; fi
         git checkout $(PUB_BRANCH)
+        git show-ref $(PUB_BRANCH)
+        git pull
       displayName: 'Git check & switch branch'
 
     - bash: |
@@ -165,5 +167,6 @@ jobs:
 
     - bash: |
         git status
+        git show-ref $(PUB_BRANCH)
         git push https://$(PAT_GHOST)@github.com/Lightning-AI/tutorials.git $(PUB_BRANCH)
       displayName: 'Finish push'

.github/workflows/ci_checks.yml

@@ -15,4 +15,4 @@ concurrency:
 jobs:
 
   check-schema:
-    uses: Lightning-AI/utilities/.github/workflows/check-schema.yml@v0.5.0
+    uses: Lightning-AI/utilities/.github/workflows/check-schema.yml@v0.9.0

.github/workflows/ci_docs.yml

@@ -99,9 +99,7 @@ jobs:
 
       - name: Make Documentation
         working-directory: ./_docs
-        run: |
-          # First run the same pipeline as Read-The-Docs
-          make html --debug SPHINXOPTS="-W --keep-going" -b linkcheck
+        run: make html --jobs $(nproc) --debug SPHINXOPTS="-W --keep-going" linkcheck
 
       - name: Upload built docs
         uses: actions/upload-artifact@v3

.github/workflows/ci_test-acts.yml

@@ -47,10 +47,9 @@ jobs:
     - name: Install requirements
       run: |
         pip --version
-        pip install -q -r .actions/requires.txt
-        pip install -q "pytest==6.*" coverage jupytext
+        pip install -q -r .actions/requires.txt -r _requirements/test.txt
         # this is needed to be able to run package version parsing test
-        pip install -q matplotlib -r _requirements/default.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html
+        pip install -q -r _requirements/default.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html
 
     - name: Prepare dummy inputs
       run: |

.github/workflows/docs-deploy.yml

@@ -47,7 +47,7 @@ jobs:
         run: make html --jobs $(nproc)
 
       - name: Deploy 🚀
-        uses: JamesIves/[email protected].1
+        uses: JamesIves/[email protected].3
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
           branch: gh-pages # The branch the action should deploy to.

.gitignore

@@ -129,3 +129,9 @@ dmypy.json
 .pyre/
 
 .idea/
+
+# data artifacts
+logs/
+lightning_logs/
+cifar-10-batches-py
+*.tar.gz

.pre-commit-config.yaml

@@ -23,31 +23,31 @@ repos:
       - id: detect-private-key
 
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.3.1
+    rev: v3.8.0
     hooks:
       - id: pyupgrade
         args: [--py37-plus]
         name: Upgrade code
 
   - repo: https://github.com/PyCQA/docformatter
-    rev: v1.5.1
+    rev: v1.7.3
     hooks:
       - id: docformatter
         args: [--in-place, --wrap-summaries=115, --wrap-descriptions=120]
 
   - repo: https://github.com/PyCQA/isort
-    rev: 5.11.4
+    rev: 5.12.0
     hooks:
       - id: isort
 
   - repo: https://github.com/psf/black
-    rev: 22.12.0
+    rev: 23.3.0
     hooks:
       - id: black
         name: Format code
 
   - repo: https://github.com/asottile/yesqa
-    rev: v1.4.0
+    rev: v1.5.0
     hooks:
       - id: yesqa
 
@@ -60,7 +60,8 @@ repos:
           - mdformat-black
           - mdformat_frontmatter
 
-  - repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.0.276
     hooks:
-      - id: flake8
+      - id: ruff
+        args: ["--fix"]

_docs/source/conf.py

@@ -51,7 +51,7 @@
 
 # If your documentation needs a minimal Sphinx version, state it here.
 
-needs_sphinx = "4.0"
+needs_sphinx = "5.3"
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
@@ -224,8 +224,17 @@
 # -- Options for intersphinx extension ---------------------------------------
 
 # Example configuration for intersphinx: refer to the Python standard library.
-# intersphinx_mapping = {
-#     "python": ("https://docs.python.org/3", None),
-#     "torch": ("https://pytorch.org/docs/stable/", None),
-#     "numpy": ("https://docs.scipy.org/doc/numpy/", None),
-# }
+intersphinx_mapping = {
+    "python": ("https://docs.python.org/3", None),
+    "torch": ("https://pytorch.org/docs/stable/", None),
+    "numpy": ("https://docs.scipy.org/doc/numpy/", None),
+}
+
+# skip false positive linkcheck errors from anchors
+linkcheck_anchors = False
+
+# ignore all links in any CHANGELOG file
+linkcheck_exclude_documents = []
+
+# ignore the following relative links (false positive errors during linkcheck)
+linkcheck_ignore = []

_requirements/default.txt

@@ -1,5 +1,7 @@
-setuptools==65.6.3
-ipython[notebook]>=8.0.0, <8.9.0
-torch>=1.8.1, <1.14.0
-pytorch-lightning>=1.4, <1.9
+setuptools==68.0.0
+matplotlib>=3.0.0, <3.8.0
+ipython[notebook]>=8.0.0, <8.15.0
+urllib3  # for ipython
+torch>=1.8.1, <2.1.0
+pytorch-lightning>=1.4, <2.1.0
 torchmetrics>=0.7, <0.12

_requirements/devel.txt

@@ -2,5 +2,5 @@ virtualenv>=20.10
 jupytext>=1.10, <1.15  # converting
 pytest>=6.0, <7.0
 # testing with own fork with extended cell timeout
-https://github.com/Borda/nbval/archive/refs/heads/master.zip
+https://github.com/Borda/nbval/archive/refs/heads/timeout-limit.zip
 papermill>=2.3.4, <2.5.0  # render

_requirements/docs.txt

@@ -1,11 +1,11 @@
-sphinx>=4.0, <5.0
-myst-parser>=0.15
-nbsphinx>=0.8
-pandoc>=1.0
-docutils>=0.16
-sphinx-paramlinks>=0.4.0
-ipython[notebook]>=8.0.0, <8.2.0
+sphinx >5.0, <6.0
+myst-parser >=0.18.1, <3.0.0
+nbsphinx >=0.8.5, <=0.8.9
+pandoc >=1.0, <=2.3
+#docutils >=0.16
+sphinx-paramlinks >=0.5.1, <=0.5.4
+ipython[notebook] >=8.0.0, <8.2.0
 
-https://github.com/Lightning-AI/lightning_sphinx_theme/archive/master.zip#egg=pt-lightning-sphinx-theme
+pt-lightning-sphinx-theme @ https://github.com/Lightning-AI/lightning_sphinx_theme/archive/master.zip
 
 -r ../.actions/requires.txt

_requirements/test.txt

@@ -0,0 +1,5 @@
+coverage>=5.0
+codecov>=2.1
+pytest>=6.0
+pytest-cov
+jupytext

course_UvA-DL/01-introduction-to-pytorch/.meta.yml

@@ -1,14 +1,15 @@
 title: "Tutorial 1: Introduction to PyTorch"
 author: Phillip Lippe
 created: 2021-08-27
-updated: 2021-11-29
+updated: 2023-03-14
 license: CC BY-SA
 description: |
   This tutorial will give a short introduction to PyTorch basics, and get you setup for writing your own neural networks.
   This notebook is part of a lecture series on Deep Learning at the University of Amsterdam.
   The full list of tutorials can be found at https://uvadlc-notebooks.rtfd.io.
 requirements:
   - matplotlib
+  - lightning>=2.0.0rc0
 accelerator:
   - CPU
   - GPU

course_UvA-DL/01-introduction-to-pytorch/Introduction_to_PyTorch.py

@@ -25,18 +25,18 @@
 import time
 
 import matplotlib.pyplot as plt
+
+# %matplotlib inline
+import matplotlib_inline.backend_inline
 import numpy as np
 import torch
 import torch.nn as nn
 import torch.utils.data as data
-
-# %matplotlib inline
-from IPython.display import set_matplotlib_formats
 from matplotlib.colors import to_rgba
 from torch import Tensor
 from tqdm.notebook import tqdm  # Progress bar
 
-set_matplotlib_formats("svg", "pdf")
+matplotlib_inline.backend_inline.set_matplotlib_formats("svg", "pdf")  # For export
 
 # %% [markdown]
 # ## The Basics of PyTorch
@@ -185,7 +185,7 @@
 print("X2 (after)", x2)
 
 # %% [markdown]
-# In-place operations are usually marked with a underscore postfix (e.g. "add_" instead of "add").
+# In-place operations are usually marked with a underscore postfix (for example `torch.add_` instead of `torch.add`).
 #
 # Another common operation aims at changing the shape of a tensor.
 # A tensor of size (2,3) can be re-organized to any other shape with the same number of elements (e.g. a tensor of size (6), or (3,2), ...).
@@ -455,7 +455,7 @@
 
 # Additionally, some operations on a GPU are implemented stochastic for efficiency
 # We want to ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 # %% [markdown]
@@ -601,10 +601,11 @@ def forward(self, x):
 
 class XORDataset(data.Dataset):
     def __init__(self, size, std=0.1):
-        """
-        Inputs:
-            size - Number of data points we want to generate
-            std - Standard deviation of the noise (see generate_continuous_xor function)
+        """XORDataset.
+
+        Args:
+            size: Number of data points we want to generate
+            std: Standard deviation of the noise (see generate_continuous_xor function)
         """
         super().__init__()
         self.size = size
@@ -800,7 +801,6 @@ def train_model(model, optimizer, data_loader, loss_module, num_epochs=100):
     # Training loop
     for epoch in tqdm(range(num_epochs)):
         for data_inputs, data_labels in data_loader:
-
             # Step 1: Move input data to device (only strictly necessary if we use GPU)
             data_inputs = data_inputs.to(device)
             data_labels = data_labels.to(device)
@@ -897,7 +897,6 @@ def eval_model(model, data_loader):
 
     with torch.no_grad():  # Deactivate gradients for the following code
         for data_inputs, data_labels in data_loader:
-
             # Determine prediction of model on dev set
             data_inputs, data_labels = data_inputs.to(device), data_labels.to(device)
             preds = model(data_inputs)

course_UvA-DL/02-activation-functions/.meta.yml

@@ -1,7 +1,7 @@
 title: "Tutorial 2: Activation Functions"
 author: Phillip Lippe
 created: 2021-08-27
-updated: 2021-08-27
+updated: 2023-03-14
 license: CC BY-SA
 description: |
   In this tutorial, we will take a closer look at (popular) activation functions and investigate their effect on optimization properties in neural networks.
@@ -14,6 +14,7 @@ requirements:
   - torchvision
   - matplotlib
   - seaborn
+  - lightning>=2.0.0rc0
 accelerator:
   - CPU
   - GPU

course_UvA-DL/02-activation-functions/Activation_Functions.py

@@ -11,6 +11,9 @@
 from urllib.error import HTTPError
 
 import matplotlib.pyplot as plt
+
+# %matplotlib inline
+import matplotlib_inline.backend_inline
 import numpy as np
 import seaborn as sns
 import torch
@@ -19,14 +22,11 @@
 import torch.optim as optim
 import torch.utils.data as data
 import torchvision
-
-# %matplotlib inline
-from IPython.display import set_matplotlib_formats
 from torchvision import transforms
 from torchvision.datasets import FashionMNIST
 from tqdm.notebook import tqdm
 
-set_matplotlib_formats("svg", "pdf")  # For export
+matplotlib_inline.backend_inline.set_matplotlib_formats("svg", "pdf")  # For export
 sns.set()
 
 # %% [markdown]
@@ -64,7 +64,7 @@ def set_seed(seed):
 
 # Additionally, some operations on a GPU are implemented stochastic for efficiency
 # We want to ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 # Fetching the device that will be used throughout this notebook
@@ -141,6 +141,7 @@ def __init__(self):
 # Both the sigmoid and tanh activation can be also found as PyTorch functions (`torch.sigmoid`, `torch.tanh`) or as modules (`nn.Sigmoid`, `nn.Tanh`).
 # Here, we implement them by hand:
 
+
 # %%
 class Sigmoid(ActivationFunction):
     def forward(self, x):
@@ -166,6 +167,7 @@ def forward(self, x):
 #
 # Let's implement the four activation functions below:
 
+
 # %%
 class ReLU(ActivationFunction):
     def forward(self, x):
@@ -213,6 +215,7 @@ def get_grads(act_fn, x):
     Args:
         act_fn: An object of the class "ActivationFunction" with an implemented forward pass.
         x: 1D input tensor.
+
     Returns:
         A tensor with the same size of x containing the gradients of act_fn at x.
     """
@@ -277,7 +280,8 @@ def vis_act_fn(act_fn, ax, x):
 # %%
 class BaseNetwork(nn.Module):
     def __init__(self, act_fn, input_size=784, num_classes=10, hidden_sizes=[512, 256, 256, 128]):
-        """
+        """Base Network.
+
         Args:
             act_fn: Object of the activation function that should be used as non-linearity in the network.
             input_size: Size of the input images in pixels
@@ -429,7 +433,8 @@ def save_model(model, model_path, model_name):
 
 # %%
 def visualize_gradients(net, color="C0"):
-    """
+    """Visualize gradients.
+
     Args:
         net: Object of class BaseNetwork
         color: Color in which we want to visualize the histogram (for easier separation of activation functions)