sinabs 3.0.4.dev2__tar.gz → 3.1.0__tar.gz

{sinabs-3.0.4.dev2 → sinabs-3.1.0}/.github/workflows/ci-pipeline.yml

@@ -16,8 +16,15 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.10"]
-        torch-version: ["2.0.0",]
+        python-version: ["3.10", "3.11", "3.12"]
+        torch-version: ["2.0.0", "2.8.0"]
+        exclude:
+          - python-version: "3.10"
+            torch-version: "2.8.0"
+          - python-version: "3.11"
+            torch-version: "2.8.0"
+          - python-version: "3.12"
+            torch-version: "2.0.0"
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
@@ -41,10 +48,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - name: Setup Python 3.8
+      - name: Setup Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: 3.12
       - name: Generate coverage report
         run: |
           sudo apt-get update && sudo apt-get -y install libglu1-mesa
@@ -63,10 +70,10 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - name: Setup Python 3.10
+      - name: Setup Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: "3.10.18"
+          python-version: "3.12"
       - name: Install dependencies
         run: |
           sudo apt-get update && sudo apt-get -y install libglu1-mesa
@@ -85,10 +92,10 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - name: Set up Python 3.8
+      - name: Set up Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: 3.12
       - name: Install build packages
         run: pip install wheel pbr setuptools
       - name: Build a binary wheel and a source tarball

{sinabs-3.0.4.dev2 → sinabs-3.1.0}/AUTHORS

@@ -22,6 +22,7 @@ Vanessa Leite <vanessa.leite@synsense.ai>
 Vanessa Leite <vanessa@ini.uzh.ch>
 Vanessa Leite <vanessinhaleite.cp.ufma@gmail.com>
 Vanessa Leite <vrcleite@gmail.com>
+Willian Girao <williansoaresgirao@gmail.com>
 Willian-Girao <williansoaresgirao@gmail.com>
 Yalun Hu <yalun.hu@synsense.ai>
 Yalun_Hu <yalun.hu@synsense.ai>

sinabs-3.1.0/PKG-INFO

@@ -0,0 +1,107 @@
+Metadata-Version: 2.4
+Name: sinabs
+Version: 3.1.0
+Summary: SynSense Spiking Neural Network simulator for deep neural networks (DNNs).
+Author: SynSense (formerly AiCTX)
+Author-email: support@synsense.ai
+License: Apache 2.0
+Project-URL: Source code, https://github.com/synsense/sinabs
+Project-URL: Documentation, https://readthedocs.org/projects/sinabs/
+Keywords: spiking neural networks,machine learning,SNN,DYNAPCNN,Speck
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: AUTHORS
+Requires-Dist: pbr
+Requires-Dist: numpy
+Requires-Dist: torch>=1.8
+Requires-Dist: nir<=1.0.4
+Requires-Dist: nirtorch
+Requires-Dist: samna>=0.33
+Requires-Dist: matplotlib
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: summary
+
+[![PyPI - Package](https://img.shields.io/pypi/v/sinabs.svg)](https://pypi.org/project/sinabs/)
+[![Documentation Status](https://readthedocs.org/projects/sinabs/badge/?version=main)](https://sinabs.readthedocs.io)
+[![codecov](https://codecov.io/gh/synsense/sinabs/branch/develop/graph/badge.svg?token=JPGAW4SH1W)](https://codecov.io/gh/synsense/sinabs)
+[![PyPI - Downloads](https://img.shields.io/pypi/dd/sinabs)](https://pepy.tech/project/sinabs)
+[![Discord](https://img.shields.io/discord/852094154188259338)](https://discord.gg/V6FHBZURkg)
+![sinabs](docs/_static/sinabs-logo-lowercase-whitebg.png)
+
+Sinabs (Sinabs Is Not A Brain Simulator) is a python library for the development and implementation of Spiking Convolutional Neural Networks (SCNNs).
+The library implements several layers that are `spiking` equivalents of CNN layers.
+In addition it provides support to import CNN models implemented in torch conveniently to test their `spiking` equivalent implementation.
+This project is managed by SynSense (former aiCTX AG).
+
+The `sinabs-dynapcnn` was incorporated to this project, and it enables porting sinabs models to chips and dev-kits with DYNAP-CNN technology.
+
+
+Installation
+------------
+For the stable release on the main branch:
+```
+pip install sinabs
+```
+or (thanks to [@Tobias-Fischer](https://github.com/Tobias-Fischer))
+```
+conda install -c conda-forge sinabs
+```
+
+For the latest pre-release on the develop branch that passed the tests:
+```
+pip install sinabs --pre
+```
+The package has been tested on the following configurations
+[![](http://github-actions.40ants.com/synsense/sinabs/matrix.svg?only=ci.multitest)](https://github.com/synsense/sinabs)
+
+
+Documentation and Examples
+--------------------------
+[https://sinabs.readthedocs.io/](https://sinabs.readthedocs.io/)
+
+Questions? Feedback?
+--------------------
+Please join us on the [#sinabs Discord channel](https://discord.gg/V6FHBZURkg)!
+
+- If you would like to report bugs or push any changes, you can do this on our [github repository](https://github.com/synsense/sinabs/issues).
+
+License
+-------
+Sinabs is published under Apache v2.0. See the LICENSE file for details.
+
+
+Contributing to Sinabs
+------------------------
+Checkout the [contributing](https://sinabs.readthedocs.io/en/develop/about/contributing.html) page for more info.
+
+
+Citation
+--------
+
+In case you find this software library useful for your work please consider citing it as follows:
+
+```
+@software{sinabs,
+author = {Sheik, Sadique and Lenz, Gregor  and Bauer, Felix and Kuepelioglu, Nogay },
+doi = {10.5281/zenodo.8385545},
+license = {Apache-2.0},
+title = {{SINABS: A simple Pytorch based SNN library specialised for Speck}},
+url = {https://github.com/synsense/sinabs}
+}
+```
+

{sinabs-3.0.4.dev2 → sinabs-3.1.0}/docs/about/differences.md

@@ -1,8 +1,8 @@
 How is Sinabs different?
 ========================
 
-There are many SNN simulators out there. What does Sinabs do differently? Sinabs is meant to extend PyTorch by adding stateful and spiking layers, which can then take full advantage of the optimised, gradient-based training mechanisms. You might find that the design of our sequential models differs slightly from that of recurrent layers in PyTorch, as we do not pass the state as an input or receive it as output. We do this so that we can be compatible with the nn.Sequential architecture, without having to manually define the flow of tensors between layers. 
+There are many SNN simulators out there. What does Sinabs do differently? Sinabs is meant to extend PyTorch by adding stateful and spiking layers, which can then take full advantage of the optimised, gradient-based training mechanisms. You might find that the design of our sequential models differs slightly from that of recurrent layers in PyTorch, as we do not pass the state as an input or receive it as output. We do this so that we can be compatible with the nn.Sequential architecture, without having to manually define the flow of tensors between layers.
 
 What is the difference between Rockpool and Sinabs?
 ---------------------------------------------------
-Rockpool provides multiple computational backends such as Jax, Nest or PyTorch and wraps its own api around it! That allows for powerful abstractions and many additional features such as graph tracing, support for continuous time systems and neuromorphic hardware. Sinabs on the other hand focuses on simplicity: Built exclusively on PyTorch, it's meant to be a thin layer that adds support for spiking layers that are not part of PyTorch. Traditionally, Sinabs added support for SynSense's convolutional neuromorphic hardware (Dynap-CNN), while Rockpool focuses on SynSense's hardware for lower-dimensional signals (Xylo). You can read about both hardware architectures [here](https://www.synsense-neuromorphic.com/technology). That means that Sinabs comes with built-in weight transfer functionality which converts a pre-trained ANN to an SNN, because vision models often have strong spatial dependencies. Rockpool on the other hand adds support for analog audio frontends and exact hardware simulation in software. 
+Rockpool provides multiple computational backends such as Jax, Nest or PyTorch and wraps its own api around it! That allows for powerful abstractions and many additional features such as graph tracing, support for continuous time systems and neuromorphic hardware. Sinabs on the other hand focuses on simplicity: Built exclusively on PyTorch, it's meant to be a thin layer that adds support for spiking layers that are not part of PyTorch. Traditionally, Sinabs added support for SynSense's convolutional neuromorphic hardware (Dynap-CNN), while Rockpool focuses on SynSense's hardware for lower-dimensional signals (Xylo). You can read about both hardware architectures [here](https://www.synsense.ai/products/speck-2/). That means that Sinabs comes with built-in weight transfer functionality which converts a pre-trained ANN to an SNN, because vision models often have strong spatial dependencies. Rockpool on the other hand adds support for analog audio frontends and exact hardware simulation in software.

sinabs-3.0.4.dev2/ChangeLog → sinabs-3.1.0/docs/about/release_notes.md

@@ -1,39 +1,51 @@
-CHANGES
-=======
+# Release notes
 
-v3.0.3
+## v3.1.0 (31/10/2025)
+
+* Fix tests crashing in case an unexpected board was found.
+* Fix tests that were not running for speck2fdevkit.
+* Fix error when initializing sinabs without matplotlib: matplotlib is not a sinabs dependency.
+* Add mapping of non-sequential networks
+    * Now, layers in Sinabs models can receive inputs from and send outputs to multiple layers.
+    * Deprecate `chip_layers_ordering` from DynapCNNNetwork. Use `layer2core_map` instead.
+    * Deprecate `DynapcnnCompatibleNetwork`. Use `DynapcnnNetwork` instead.
+    * Deprecate `merge_conv_bn` from `sinabs.utils`. Use `merge_bn` instead.
+
+## v3.0.4 (08/09/2025)
+
+* Update sinabs code to be consistent with Python 3.12 and Numpy > 2.0.
+* Merge Release Notes and Changelog.
+    * Remove Changelog file as it was not being used.
+* Remove Pipfile and Pipfile.lock files as they were not being used anymore.
+    * Specific/minimal library versions can be found in requirements.txt
+
+## v3.0.3 (22/07/2025)
 
 * Add function in utils to help identify issues with memory constraints when mapping a network on Speck.
 (https://sinabs.readthedocs.io/v3.0.3/api/utils.html#sinabs.utils.validate_memory_mapping_speck)
 
-v3.0.2
-------
+## v3.0.2 (10/06/2025)
 
 * Update contact email. Now, any support requests and information about contributors license agreement needs to be sent to `support@synsense.ai`.
 
-v3.0.1
-------
+## v3.0.1 (06/06/2025)
 
 * Update the release of the project when `main` branch is updated instead of `develop`
 
-v3.0.0
-------
+## v3.0.0 (06/06/2025)
 
 * Remove support for older boards following update on Samna 0.46.0
 
-v2.0.3
-------
+## v2.0.3 (18/03/2025)
 
 * Update Sinabs license to Apache 2.0
 
-v2.0.2
-------
+## v2.0.2 (23/01/2025)
 
 * Spike count plot in 'DynapcnnVisualizer' is optional 
 * `DynapcnnVisualizer` allows custom JIT filters to make readout predictions
 
-v2.0.0
-------
+## v2.0.0 (14/03/2024)
 
 * Fix typos and broken links in the documentation
 * Move instructions for adding new device to FAQ
@@ -66,8 +78,7 @@ v2.0.0
 * Remove easy-install command
 * Add graphviz dependency
 
-v1.2.10
--------
+## v1.2.10 (07/12/2023)
 
 * Update codecov.yml
 * Update ci-pipeline.yml
@@ -97,8 +108,7 @@ v1.2.10
 * set default value to 1 for stride in SumPool2d
 * updated nir to support Flatten and SumPool2d
 
-v1.2.9
-------
+## v1.2.9 (31/08/2023)
 
 * Add unit test to ensure that subract value of MembraneSubtract can be a tensor
 * Correct test whether subtract value is None
@@ -165,8 +175,7 @@ v1.2.9
 * add nir IF support
 * updated Sinabs to latest NIR
 
-1.2.8
------
+## 1.2.8 (10/07/2023)
 
 * add nir and nirtorch to requirements
 * implemented sequential for from\_nir
@@ -181,8 +190,7 @@ v1.2.9
 * wip conversion from nir to sinabs
 * Fix issue #99, add unit test
 
-v1.2.6
-------
+## v1.2.6 (30/06/2023)
 
 * change nmnist tutorial title
 * added NMNIST tutorial
@@ -279,15 +287,13 @@ v1.2.6
 * try another way install graphviz
 * fix CI pipeline failure
 
-v1.2.5
-------
+## v1.2.5 (24/04/2023)
 
 * make contact title bold like the others
 * add contact section to documentation
 * checked tests pass on mac
 
-v1.2.4
-------
+## v1.2.4 (05/04/2023)
 
 * replace torch.inf with math.inf
 * ignore data and cache directories
@@ -298,14 +304,12 @@ v1.2.4
 * added update keyring to gitlab-ci
 * renamed test
 
-v1.2.3
-------
+## v1.2.3
 
 * fix synops/s for Linear layers when no Squeeze layers are used in network
 * update pre-commit config
 
-v1.2.2
-------
+## v1.2.2 (17/03/2023)
 
 * expand saved input in spiking layers for analyzer
 * derive spiking layer stats from single saved output tensor and also save input
@@ -317,16 +321,16 @@ v1.2.2
 * update ChangeLog
 * add speck2f module devkit support and remove speck2f characterization board support
 
-v1.2.1
-------
+## v1.2.1 (23/02/2023)
 
 * distinguish between accumulated and mini batch stats for firing rates
 * distinguish between accumulated and mini batch statistics in SNNAnalyzer for synops
 * only compute connection\_map once in SynopsHook
 * detach synops accumulation inbetween mini batches for SNNAnalyzer
 
-v1.2.0
-------
+## v1.2.0 (15/02/2023)
+
+Included the SNNAnalyzer module to collect model statistics such as number of synops or neurons automatically.
 
 * update release notes
 * make sure deconvolve outputs same size as conv input in SNNAnalyzer
@@ -403,8 +407,7 @@ v1.2.0
 * update synops\_loss\_ann notebook
 * use consistent American spelling of analyzer
 
-v1.1.6
-------
+## v1.1.6 (08/12/2022)
 
 * make min\_vem and spike\_thresholds parameters do that they're included in state\_dict
 * Detach recordings before plotting
@@ -448,8 +451,7 @@ v1.1.6
 * Do not sleep while resetting the states when the function is called. Stop the input graph, while the neuron values are written. Sleep for a bit and then start the graph again
 * Fix to the bug
 
-v1.1.5
-------
+## v1.1.5 (25/11/2022)
 
 * Fix backward pass for MaxSpike
 * update ChangeLog after add support of speck2e
@@ -477,8 +479,7 @@ v1.1.5
 * Requirements for samna version updated
 * Change to get the same functionality in 'to()' method in samna Version: 0.21.2.0
 
-v1.1.4
-------
+## v1.1.4 (18/11/2022)
 
 * autoformat all docstrings using docformatter
 * fix bug where added\_spike\_output is a ReLU
@@ -487,14 +488,12 @@ v1.1.4
 * Update ci-pipeline.yml
 * Update ci-pipeline.yml
 
-v1.1.3
-------
+## v1.1.3 (17/11/2022)
 
 * Update ci-pipeline.yml
 * add generic reset\_states and zero\_grad utility functions
 
-v1.1.2
-------
+## v1.1.2 (16/11/2022)
 
 * make sure that add\_spike\_output doesn't add spiking layer in original ANN
 * removed unused imports
@@ -505,8 +504,7 @@ v1.1.2
 * add documentation about how to release a new Sinabs version
 * Hotfix new arg\_dict
 
-v1.1.1
-------
+## v1.1.1 (02/11/2022)
 
 * add arg\_dict property to StatefulLayer
 * Update ci-pipeline.yml
@@ -518,16 +516,14 @@ v1.1.1
 * add a replace\_module function that will replace specific layer according to a mapper\_fn. Reworked from\_torch
 * requirement bumped to 1.0.7
 
-v1.0.7
-------
+## v1.0.7 (27/10/2022)
 
 * check for pytorch version under test and either call testing.assert\_close or assert\_allclose depending on the version
 * using torch.equal instead of np equal
 * tests fixed
 * fixing test
 
-v1.0.6
-------
+## v1.0.6
 
 * added zero\_grad to network
 * wip enable learning
@@ -537,8 +533,7 @@ v1.0.6
 * added zero\_grad function
 * updates to latest sinabs requirements
 
-v1.0.5
-------
+## v1.0.5 (21/10/2022)
 
 * add utils functions to documentation
 * update tutorial notebooks to use batch\_size or num\_timesteps for from\_model
@@ -547,8 +542,7 @@ v1.0.5
 * exclude samna log files
 * get rid of test warnings: Dropout instead of Dropout2d, no autograd fn instantiation, torch.arange
 
-v1.0.4
-------
+## v1.0.4 (05/10/2022)
 
 * more docstring updates for layers plus cross-references in API documentation
 * add shape and attributes to layer docstrings
@@ -558,27 +552,24 @@ v1.0.4
 * add Repeat auxiliary layer
 * Update ci-pipeline.yml
 
-v1.0.3
-------
+## v1.0.3 (28/09/2022)
 
 * exclude generated authors / changelog files
 * Removed pandas dependency. Adjusted tests accordingly
 * add speck2e config builder
 
-v1.0.2
-------
+## v1.0.2 (14/09/2022)
 
 * additional minor docstring update
 * update some more docstrings for activation modules
 * doc strings updated
 
-v1.0.1
-------
+## v1.0.1 (26/08/2022)
 
+Mostly making v0.3.x stable, with a revamped documentation that includes a gallery and how-tos!
 * add release notes for v1.0.1
 
-v1.0.0
-------
+## v1.0.0
 
 * add complete tutorial notebooks since their execution is deactivated on the docs server
 * exclude some notebooks from automatic documentation build because they take very long
@@ -590,8 +581,7 @@ v1.0.0
 * first version of Sinabs gallery instead of tutorial notebook that plots neuron models
 * added pre-commit hooks for black
 
-v0.3.5
-------
+## v0.3.5 (18/08/2022)
 
 * Bump stable PyTorch version from 1.10 to 1.12 in CI pipeline
 * Fix bug in tutorial due to API update
@@ -600,8 +590,7 @@ v0.3.5
 * Fix handling of non-scalar tau\_syn
 * Prevent non-integer arguments to Squeeze class from breaking code
 
-v0.3.4
-------
+## v0.3.4 (21/06/2022)
 
 * Fix critical bug in LIF synaptic forward dynamics
 * re-naming from BufferSinkNode to BasicSinkNode
@@ -645,8 +634,7 @@ v0.3.4
 * Remove tau\_mem as a parameter from IAF
 * from\_model takes same parameters as IAF
 
-v0.3.3
-------
+## v0.3.3 (20/04/2022)
 
 * update SNN synops tutorial
 * make SNNSynopsCounter work as a loss function
@@ -658,21 +646,28 @@ v0.3.3
 * moved parse\_device\_string into utils. No need of samna to run other modules
 * added speck2b tiny support
 
-v0.3.2
-------
+## v0.3.2 (314/03/2022)
 
 * Rename remaining threshold arguments to spike\_threshold for more consistency
 * Update .gitlab-ci.yml
 * Update jupyterlab-requirements.txt
 
-v0.3.1
-------
+## v0.3.1 (23/03/2022)
 
 * Update ci-pipeline.yml
 * Update requirements.txt
 
-v0.3.0
-------
+## v0.3.0 (22/03/2022)
+
+This is a major overhaul which rewrites a large part of the package. 
+
+* Addition of leaky models such as Leaky Integrate and Fire (LIF), Exponential Leaky (ExpLeak) and Adaptive LIF (ALIF).
+* Activation module: from sinabs.activation you'll now be able to pick and choose different spike generation, reset mechanism and surrogate gradient functions. You can pass them to the neuron model (LIF, IAF, ...) of your liking if you want to alter the default behavior.
+* new documentation on readthedocs
+* SpikingLayer has been renamed to IAF (Integrate and Fire).
+* State variable names changed and new ones have been added: 'state' is now called 'v_mem' and 'i_syn' is added for neuron layers that use tau_syn.
+* New neuron features: support for recurrent connections, recording internal states, normalising inputs by taus, initialisation with shape and more.
+* We moved our repo to Github and changed the CI pipeline to Github actions.
 
 * add basic parameter printing in \_\_repr\_\_
 * Update ci-pipeline.yml
@@ -791,8 +786,13 @@ v0.3.0
 * tau\_mem for LIF neurons is now always calculated on CPU and transferred to original device, for better numerical comparison with SLAYER LIF layer
 * only zero gradients if state is initialised
 
-v0.2.1
-------
+## v0.2.1 (22/02/2022)
+
+* TorchLayer renamed to Layer
+    * Added a depricated class TorchLayer with warning
+* Added some new layer types
+    * BPTT enabled spike activation layer
+    * SpikingTemporalConv1dLayer
 
 * added pip install
 * added requirements
@@ -1144,8 +1144,7 @@ v0.2.1
 * fixed docs, removed commented-out areas
 * removed dependency on samna for validation, and on SpikingLayerBPTT
 
-v0.2.0
-------
+## v0.2.0
 
 * Threshold gradient scaled by threshold (Bug fix)
 * updated docs, removed exclude\_negative\_spikes from fromtorch (no effect)
@@ -1324,8 +1323,7 @@ v0.2.0
 * Depricated TorchLayer added
 * merged master to bptt\_devel
 
-v0.1.dev7
----------
+## v0.1.dev7 (09/04/2020)
 
 * install m2r with hotfix for new version of sphinx
 * changed membrane\_subtract and reset defaults, some cleanup
@@ -1504,8 +1502,7 @@ v0.1.dev7
 * merged
 * fixed typos in readme
 
-v0.1.0
-------
+## v0.1.0
 
 * fixed version number
 * removed contrib branch

{sinabs-3.0.4.dev2 → sinabs-3.1.0}/docs/contact.md

@@ -1,5 +1,5 @@
 # **CONTACT US**
 
-Are you using Sinabs to train your networks? Do you have access to SynSense hardware and need help figuring something out? Found a bug? It's normally easiest to reach SynSense developers on the [SynSense Discord](https://discord.gg/V6FHBZURkg) server. There we have dedicated channels regarding Sinabs and our hardware. 
+Are you using Sinabs to train your networks? Do you have access to SynSense hardware and need help figuring something out? Found a bug? It's normally easiest to reach SynSense developers on the [SynSense Discord](https://discord.gg/9yY3uyJV) server. There we have dedicated channels regarding Sinabs and our hardware.
 
 If you don't have Discord, you can also start a discussion on [Github](https://github.com/synsense/sinabs/discussions)!

{sinabs-3.0.4.dev2 → sinabs-3.1.0}/docs/getting_started/quickstart.ipynb

@@ -28,15 +28,9 @@
     "\n",
     "model = nn.Sequential(\n",
     "    nn.Linear(16, 64),\n",
-    "    sl.LIF(\n",
-    "        tau_mem=10.0,\n",
-    "        surrogate_grad_fn=sinabs.activation.SingleExponential()\n",
-    "    ),\n",
+    "    sl.LIF(tau_mem=10.0, surrogate_grad_fn=sinabs.activation.SingleExponential()),\n",
     "    nn.Linear(64, 4),\n",
-    "    sl.LIF(\n",
-    "        tau_mem=10.0,\n",
-    "        surrogate_grad_fn=sinabs.activation.SingleExponential()\n",
-    "    ),\n",
+    "    sl.LIF(tau_mem=10.0, surrogate_grad_fn=sinabs.activation.SingleExponential()),\n",
     ")"
    ]
   },

{sinabs-3.0.4.dev2 → sinabs-3.1.0}/docs/how_tos/activations.ipynb

@@ -258,7 +258,9 @@
     "x = torch.linspace(-0.5, 3.5, 500)\n",
     "plt.plot(x, sina.Heaviside(window=0.5)(v_mem=x, spike_threshold=1.0), label=\"Heaviside\")\n",
     "plt.plot(x, sina.MultiGaussian()(v_mem=x, spike_threshold=1.0), label=\"MultiGaussian\")\n",
-    "plt.plot(x, sina.SingleExponential()(v_mem=x, spike_threshold=1.0), label=\"SingleExponential\")\n",
+    "plt.plot(\n",
+    "    x, sina.SingleExponential()(v_mem=x, spike_threshold=1.0), label=\"SingleExponential\"\n",
+    ")\n",
     "\n",
     "plt.xlabel(\"Membrane potential v_mem\")\n",
     "plt.ylabel(\"derivative of output activation\")\n",

{sinabs-3.0.4.dev2 → sinabs-3.1.0}/docs/how_tos/custom_hooks.ipynb

@@ -27,6 +27,7 @@
     "from sinabs import layers as sl\n",
     "import sinabs.hooks\n",
     "\n",
+    "\n",
     "# - Define SNN\n",
     "class SNN(nn.Sequential):\n",
     "    def __init__(self, batch_size):\n",
@@ -46,6 +47,7 @@
     "            sl.UnflattenTime(batch_size=batch_size),\n",
     "        )\n",
     "\n",
+    "\n",
     "batch_size = 5\n",
     "snn = SNN(batch_size=batch_size)"
    ]
@@ -162,7 +164,7 @@
    ],
    "source": [
     "# Forward pass\n",
-    "rand_input_spikes = (torch.ones((batch_size, 10, 1, 28, 28)) ).float()\n",
+    "rand_input_spikes = (torch.ones((batch_size, 10, 1, 28, 28))).float()\n",
     "snn(rand_input_spikes)\n",
     "\n",
     "# Access and print hook data\n",
@@ -170,7 +172,9 @@
     "    if hasattr(layer, \"hook_data\"):\n",
     "        print(f\"Layer {idx}:\")\n",
     "        print(f\"\\tBatch size: {layer.hook_data['batch_size']}\")\n",
-    "        print(f\"\\tShape: {layer.hook_data['neuron_shape']} - {layer.hook_data['num_neurons']} neurons in total\")"
+    "        print(\n",
+    "            f\"\\tShape: {layer.hook_data['neuron_shape']} - {layer.hook_data['num_neurons']} neurons in total\"\n",
+    "        )"
    ]
   },
   {