deploy: e52ecba

Author: C-Achard

_images/inference_results_example.png

@@ -145,7 +145,7 @@ Simply load the csv file in the notebook and use the provided functions to plot
 Unsupervised model - WNet3D
 --------------------------------
 
-| The `WNet3D model` is a fully unsupervised model used to segment images without any labels.
+| The `WNet3D model` is a fully self-supervised model used to segment images without any labels.
 | It functions similarly to the above models, with a few notable differences.
 
 .. _WNet3D model: https://arxiv.org/abs/1711.08506
@@ -159,11 +159,17 @@ For the best inference performance, the model should be retrained on images of t
 Please see :ref:`training_wnet` for more details on how to train your own model.
 
 .. hint::
-  | WNet3D, as an unsupervised model, may not always output the background class in the same dimension.
-  | This might cause the result from inference to appear densely populated.
+  | WNet3D, as an unsupervised model, may not always output the background and foreground class in the same dimension, as this depends on initial conditions.
+  | This might cause the result from inference to appear densely populated or empty.
   | The plugin will automatically attempt to show the foreground class, but this might not always succeed.
   | If the displayed output seems dominated by the background, you can manually adjust the visible class. To do this, **use the slider positioned at the bottom of the napari window**.
 
+.. figure:: ../images/inference_results_example.png
+    :alt: An example of inference with WNet3D on a 3D volume
+    :align: center
+
+    Example of inference with WNet3D on a 3D volume
+
 Source code
 --------------------------------
 * :doc:`../code/_autosummary/napari_cellseg3d.code_plugins.plugin_model_inference`

_sources/source/guides/inference_module_guide.rst

@@ -443,7 +443,7 @@ <h2> Contents </h2>
 <figure class="align-center" id="id1">
 <img alt="../../_images/plugin_crop.png" src="../../_images/plugin_crop.png" />
 <figcaption>
-<p><span class="caption-number">Fig. 11 </span><span class="caption-text">Layout of the cropping module</span><a class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 12 </span><span class="caption-text">Layout of the cropping module</span><a class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 <p><strong>Cropping</strong> allows you to crop your volumes and labels dynamically,
@@ -494,7 +494,7 @@ <h2>Interface &amp; functionalities<a class="headerlink" href="#interface-functi
 <figure class="align-center" id="id2">
 <img alt="../../_images/cropping_process_example.png" src="../../_images/cropping_process_example.png" />
 <figcaption>
-<p><span class="caption-number">Fig. 12 </span><span class="caption-text">Example of the cropping process interface.</span><a class="headerlink" href="#id2" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 13 </span><span class="caption-text">Example of the cropping process interface.</span><a class="headerlink" href="#id2" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 <p>Once you have launched the review process, you will gain control over three sliders, which will let

searchindex.js

@@ -467,7 +467,7 @@ <h2>Setting up images and labels<a class="headerlink" href="#setting-up-images-a
 <figure class="align-center" id="id1">
 <a class="reference internal image-reference" href="../../_images/init_image_labels.png"><img alt="../../_images/init_image_labels.png" src="../../_images/init_image_labels.png" style="width: 1188.0px; height: 738.0px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 13 </span><span class="caption-text">Example of an anisotropic volume (i.e., often times the z resolution is not the same as x and y) and its associated labels.</span><a class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 14 </span><span class="caption-text">Example of an anisotropic volume (i.e., often times the z resolution is not the same as x and y) and its associated labels.</span><a class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 <div class="admonition note">
@@ -499,7 +499,7 @@ <h3>Cropping<a class="headerlink" href="#cropping" title="Permalink to this head
 <figure class="align-center" id="id2">
 <img alt="../../_images/cropping_process_example.png" src="../../_images/cropping_process_example.png" />
 <figcaption>
-<p><span class="caption-number">Fig. 14 </span><span class="caption-text">Cropping module layout</span><a class="headerlink" href="#id2" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 15 </span><span class="caption-text">Cropping module layout</span><a class="headerlink" href="#id2" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 </section>
@@ -522,7 +522,7 @@ <h3>Label conversion utility<a class="headerlink" href="#label-conversion-utilit
 <figure class="align-center" id="id3">
 <a class="reference internal image-reference" href="../../_images/converted_labels.png"><img alt="../../_images/converted_labels.png" src="../../_images/converted_labels.png" style="width: 680.0px; height: 384.0px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 15 </span><span class="caption-text">Example of instance labels from above converted to semantic labels</span><a class="headerlink" href="#id3" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 16 </span><span class="caption-text">Example of instance labels from above converted to semantic labels</span><a class="headerlink" href="#id3" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 <p>To remove small objects, or to convert a single image, use the <strong>`CTRL+O`</strong> shortcut to open the image you wish to manipulate.
@@ -587,7 +587,7 @@ <h3>Training Guide<a class="headerlink" href="#training-guide" title="Permalink
 <figure class="align-center" id="id4">
 <img alt="../../_images/plots_train.png" src="../../_images/plots_train.png" />
 <figcaption>
-<p><span class="caption-number">Fig. 16 </span><span class="caption-text">Plots displayed by the training module after 40 epochs</span><a class="headerlink" href="#id4" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 17 </span><span class="caption-text">Plots displayed by the training module after 40 epochs</span><a class="headerlink" href="#id4" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 <ul class="simple">
@@ -662,7 +662,7 @@ <h3>Labels review<a class="headerlink" href="#labels-review" title="Permalink to
 <figure class="align-center" id="id5">
 <img alt="../../_images/review_process_example.png" src="../../_images/review_process_example.png" />
 <figcaption>
-<p><span class="caption-number">Fig. 17 </span><span class="caption-text">Layout of the review module</span><a class="headerlink" href="#id5" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 18 </span><span class="caption-text">Layout of the review module</span><a class="headerlink" href="#id5" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 <p>Once you finish reviewing, press the <strong>Not checked</strong> button to switch the status to
@@ -679,7 +679,7 @@ <h3>Analysis : Jupyter notebooks<a class="headerlink" href="#analysis-jupyter-no
 <figure class="align-center" id="id6">
 <img alt="../../_images/stat_plots.png" src="../../_images/stat_plots.png" />
 <figcaption>
-<p><span class="caption-number">Fig. 18 </span><span class="caption-text">Example of the plot present in the notebooks.
+<p><span class="caption-number">Fig. 19 </span><span class="caption-text">Example of the plot present in the notebooks.
 Coordinates are based on centroids, the size represents the volume, the color, and the sphericity.</span><a class="headerlink" href="#id6" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>

source/guides/cropping_module_guide.html

@@ -598,7 +598,7 @@ <h2>Plotting results<a class="headerlink" href="#plotting-results" title="Permal
 <section id="unsupervised-model-wnet3d">
 <h2>Unsupervised model - WNet3D<a class="headerlink" href="#unsupervised-model-wnet3d" title="Permalink to this heading">#</a></h2>
 <div class="line-block">
-<div class="line">The <cite>WNet3D model</cite> is a fully unsupervised model used to segment images without any labels.</div>
+<div class="line">The <cite>WNet3D model</cite> is a fully self-supervised model used to segment images without any labels.</div>
 <div class="line">It functions similarly to the above models, with a few notable differences.</div>
 </div>
 <div class="admonition note">
@@ -612,12 +612,18 @@ <h2>Unsupervised model - WNet3D<a class="headerlink" href="#unsupervised-model-w
 <div class="admonition hint">
 <p class="admonition-title">Hint</p>
 <div class="line-block">
-<div class="line">WNet3D, as an unsupervised model, may not always output the background class in the same dimension.</div>
-<div class="line">This might cause the result from inference to appear densely populated.</div>
+<div class="line">WNet3D, as an unsupervised model, may not always output the background and foreground class in the same dimension, as this depends on initial conditions.</div>
+<div class="line">This might cause the result from inference to appear densely populated or empty.</div>
 <div class="line">The plugin will automatically attempt to show the foreground class, but this might not always succeed.</div>
 <div class="line">If the displayed output seems dominated by the background, you can manually adjust the visible class. To do this, <strong>use the slider positioned at the bottom of the napari window</strong>.</div>
 </div>
 </div>
+<figure class="align-center" id="id3">
+<img alt="An example of inference with WNet3D on a 3D volume" src="../../_images/inference_results_example.png" />
+<figcaption>
+<p><span class="caption-number">Fig. 11 </span><span class="caption-text">Example of inference with WNet3D on a 3D volume</span><a class="headerlink" href="#id3" title="Permalink to this image">#</a></p>
+</figcaption>
+</figure>
 </section>
 <section id="source-code">
 <h2>Source code<a class="headerlink" href="#source-code" title="Permalink to this heading">#</a></h2>

source/guides/detailed_walkthrough.html

@@ -483,7 +483,7 @@ <h2>Parameters<a class="headerlink" href="#parameters" title="Permalink to this
 <figure class="align-right" id="id1">
 <a class="reference internal image-reference" href="../../_images/training_tab_4.png"><img alt="../../_images/training_tab_4.png" src="../../_images/training_tab_4.png" style="width: 232.0px; height: 463.0px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 19 </span><span class="caption-text">Advanced tab</span><a class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
+<p><span class="caption-number">Fig. 20 </span><span class="caption-text">Advanced tab</span><a class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
 </figcaption>
 </figure>
 <p><span class="target" id="when-using-the-wnet3d-training-module">When using the WNet3D training module</span>, the <strong>Advanced</strong> tab contains a set of additional options:</p>