Deployed with MkDocs version: 1.3.1

docs/workflows/index.html

@@ -1181,38 +1181,38 @@ <h1 id="general-workflows">General workflows</h1>
 configurations. All of the main Workflows have a dedicated, interactive notebook (.ipynb file) ready to use with explanations for each step. All
 of the workflow notebooks are located in a dedicated folder called "workflows".</p>
 <h2 id="workflow-files-descriptions">Workflow Files Descriptions</h2>
-<p><code>create_yolo_images.ipynb</code> - Prepares raw frames of some experiment for the process of training YOLO model on them. This step entails
+<p><strong><code>create_yolo_images.ipynb</code></strong> - Prepares raw frames of some experiment for the process of training YOLO model on them. This step entails
 detecting the worm in selected frames and cropping a region of pre-defined size around the worms.</p>
-<p><code>yolo_training.ipynb</code> - Used to train a YOLO model on a given dataset. The training dataset was prepared by annotating 3 the images which
+<p><strong><code>yolo_training.ipynb</code></strong> - Used to train a YOLO model on a given dataset. The training dataset was prepared by annotating 3 the images which
 were extracted using the notebook create_yolo_images. The annotation process can be done with RoboFlow, which is an online dataset
 creation and annotation tool.</p>
-<p><code>initialize_experiment.ipynb</code> - In order to run system simulations on a new experiment, first it’s essential to initialize the experiment. The
+<p><strong><code>initialize_experiment.ipynb</code></strong> - In order to run system simulations on a new experiment, first it’s essential to initialize the experiment. The
 initialization step runs the YOLO predictor on the raw experiment, detects worm’s head position in each frame and saves the detection results
 into a log. That log would be later used for simulating different control algorithms on the experiment. In addition, the background image and
 worm images are extracted from the raw frames. These can be used later during analysis, to calculate the segmentation based error. This log is
 useful since in the future the simulator can simply read worm head positions from the log, instead of using YOLO to predict worm’s head
 position in every frame of interest (which is much slower, especially on computers without a dedicated graphics card).</p>
-<p><code>simulate.ipynb</code> - Run a full system simulation on some previously initialized experiment. The simulation is ran by reading an experiment
+<p><strong><code>simulate.ipynb</code></strong> - Run a full system simulation on some previously initialized experiment. The simulation is ran by reading an experiment
 log produced by the initialization process - in each frame, worm’s head position is retrieved from the log. In this notebook it is possible to
 simulate the system with any controller and any configuration parameters, not only the ones of used for the initial experiment log. Similar to
 the initialization process, the simulation produces a log, which would be later used to analyze system’s performance and its behavior.</p>
-<p><code>analysis.ipynb</code> - This notebook is used to analyze the performance of a control algorithm (controller). A log which was produced by running
+<p><strong><code>analysis.ipynb</code></strong> - This notebook is used to analyze the performance of a control algorithm (controller). A log which was produced by running
 simulate is read and analyzed, and different plots and statistics are presented. In addition, there is an option to calculate segmentation
 evaluation-error, by counting how many pixels of the worm are outside of the microscope view. To this end, we use the background and worm
 images which were extracted during the run of intialize_experiment notebook for this experiment.</p>
-<p><code>visualize.ipynb</code> - Given a system log which was produced by simulate, this notebook is able to visually recreate the simulator’s behavior. At
+<p><strong><code>visualize.ipynb</code></strong> - Given a system log which was produced by simulate, this notebook is able to visually recreate the simulator’s behavior. At
 each frame, the position of worm’s head is drawn, the position of the microscope FOV, and also the camera FOV. This notebook is used to
 visually assess the performance and the behavior of the simulator, and to visually investigate what causes the system to misbehave.
 predictor_training - Used to train a specific simulation control algorithm. The MLPController *is an algorithm that uses a neural
 network (NN) to predict worm’s future position. Since this algorithm is NN based, it requires training. That script is responsible to train that
 NN from experiment log files, which were produced by either running initialize or simulate (doesn’t matter).</p>
-<p><code>polyfit_optimizer.ipynb</code> - This notebook is used to tune the parameters of a specific simulation control algorithm. The PolyfitController
+<p><strong><code>polyfit_optimizer.ipynb</code></strong> - This notebook is used to tune the parameters of a specific simulation control algorithm. The PolyfitController
 is an algorithm that uses polynomial-fitting to predict worm’s future position. A polynomial is fitted from past observations at previous time
 stamps, and afterwards sampled in the future time to predict worm’s position. This notebook is used to determine the optimal degree of the
 fitted polynomial, and to find the optimal weight of each past sample for the fitting process.</p>
 <h2 id="workflow-files-dependency-graph">Workflow Files Dependency Graph</h2>
 <p>
-    <img src="images/work-flowchart.png">
+    <img src="../images/work-flowchart.png">
     <em>
     Workflow outline and the dependencies between each notebook files. Blue color (rectangles) denotes an interactive notebook file, green color (diamond) denotes intermediate outputs between different files, and the global input is in yellow color (circle). 
 Dotted line denote optional dependencies.</em>
@@ -1305,11 +1305,11 @@ <h3 id="perform-system-simulation">Perform System Simulation</h3>
 <p>Decide on the platform control algorithm to be used.</p>
 <ol>
 <li>
-<p>If <strong><code>MLPController</code></strong> algorithm is chosen: the MLP controller works by a neural network that predicts future positions of the worm. If that network needs training then first run <code>predictor_training</code> notebook.
+<p>If <code>MLPController</code> algorithm is chosen: the MLP controller works by a neural network that predicts future positions of the worm. If that network needs training then first run <code>predictor_training</code> notebook.
 Note, that the neural network should be trained only once. Once the network is trained, there is no need to perform this step anymore. </p>
 </li>
 <li>
-<p>If <strong><code>PolyfitController</code></strong> algorithm is chosen, and the hyper-parameters of the controller should be tuned then first run the <code>polyfit_optimizer</code> notebook.
+<p>If <code>PolyfitController</code> algorithm is chosen, and the hyper-parameters of the controller should be tuned then first run the <code>polyfit_optimizer</code> notebook.
 Note, that the hyper-parameters of this controller should be tuned only once. Once they were tuned, there is no need to perform this step anymore. </p>
 </li>
 </ol>

reference/wtracker/eval/vlc/index.html

@@ -2854,7 +2854,7 @@ <h4 id="create_trackbar">create_trackbar</h4>
     <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
     <span class="n">val</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
     <span class="n">maxval</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
-    <span class="n">onChange</span><span class="o">=&lt;</span><span class="n">function</span> <span class="n">StreamViewer</span><span class="o">.&lt;</span><span class="k">lambda</span><span class="o">&gt;</span> <span class="n">at</span> <span class="mh">0x7f9303198160</span><span class="o">&gt;</span>
+    <span class="n">onChange</span><span class="o">=&lt;</span><span class="n">function</span> <span class="n">StreamViewer</span><span class="o">.&lt;</span><span class="k">lambda</span><span class="o">&gt;</span> <span class="n">at</span> <span class="mh">0x7f2da6548160</span><span class="o">&gt;</span>
 <span class="p">)</span>
 </code></pre></div>
 

reference/wtracker/utils/path_utils/index.html

@@ -2035,7 +2035,7 @@ <h3 id="files">Files</h3>
     <span class="n">extension</span><span class="p">:</span> <span class="s1">&#39;str&#39;</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span><span class="p">,</span>
     <span class="n">scan_dirs</span><span class="p">:</span> <span class="s1">&#39;bool&#39;</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
     <span class="n">return_full_path</span><span class="p">:</span> <span class="s1">&#39;bool&#39;</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
-    <span class="n">sorting_key</span><span class="p">:</span> <span class="s1">&#39;Callable[[str], Union[int, str]]&#39;</span> <span class="o">=</span> <span class="o">&lt;</span><span class="n">function</span> <span class="n">Files</span><span class="o">.&lt;</span><span class="k">lambda</span><span class="o">&gt;</span> <span class="n">at</span> <span class="mh">0x7f93ee7f2290</span><span class="o">&gt;</span>
+    <span class="n">sorting_key</span><span class="p">:</span> <span class="s1">&#39;Callable[[str], Union[int, str]]&#39;</span> <span class="o">=</span> <span class="o">&lt;</span><span class="n">function</span> <span class="n">Files</span><span class="o">.&lt;</span><span class="k">lambda</span><span class="o">&gt;</span> <span class="n">at</span> <span class="mh">0x7f2e907f6290</span><span class="o">&gt;</span>
 <span class="p">)</span>
 </code></pre></div>