enable scrolling and cosmetic changes

jp-ga · jp-ga · commit e30a3780ec92 · 2025-03-18T17:21:47.000-07:00
diff --git a/tutorial.ipynb b/tutorial.ipynb
@@ -2292,7 +2292,7 @@
     }
    },
    "source": [
-    "Diagnostics for generative phase space reconstruction (GPSR)\n",
+    "### Diagnostics for generative phase space reconstruction (GPSR)\n",
     "\n",
     "<img src=\"fig/gpsr_scan.png\" style=\"width:90%; margin:auto;\"/>"
    ]
@@ -2305,7 +2305,7 @@
     }
    },
    "source": [
-    "Load example GPSR dataset"
+    "### Example GPSR Dataset"
    ]
   },
   {
@@ -2333,15 +2333,6 @@
     "obs_dataset.plot_data(publication_size=True);"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "slideshow": {
-     "slide_type": "fragment"
-    }
-   },
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -2350,14 +2341,14 @@
     }
    },
    "source": [
-    "Let's inspect the GPSR dataset.\n",
+    "### Let's inspect the GPSR dataset.\n",
     "\n",
     "The dataset is a custom PyTorch `Dataset`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 50,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -2368,14 +2359,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "gpsr dataset class: <class 'gpsr.datasets.SixDReconstructionDataset'>\n",
-      "gpsr dataset parent class: <class 'torch.utils.data.dataset.Dataset'>\n"
+      "<class 'gpsr.datasets.SixDReconstructionDataset'>\n",
+      "<class 'torch.utils.data.dataset.Dataset'>\n"
      ]
     }
    ],
    "source": [
-    "print(f'gpsr dataset class: {obs_dataset.__class__}')\n",
-    "print(f'gpsr dataset parent class: {obs_dataset.__class__.__bases__[0].__bases__[0]}')"
+    "print(obs_dataset.__class__)\n",
+    "print(obs_dataset.__class__.__bases__[0].__bases__[0])"
    ]
   },
   {
@@ -2391,7 +2382,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 51,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -2402,12 +2393,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "dataset parameters shape: torch.Size([2, 2, 5, 3])\n"
+      "torch.Size([2, 2, 5, 3])\n"
      ]
     }
    ],
    "source": [
-    "print(f'dataset parameters shape: {obs_dataset.six_d_params.shape}')"
+    "print(obs_dataset.six_d_params.shape)"
    ]
   },
   {
@@ -2497,6 +2488,8 @@
     }
    },
    "source": [
+    "### GPSR Diagnostics Lattice\n",
+    "\n",
     "Lattice creation is done using a wrapper class which contains the Cheetah `Segment` for tracking, the cheetah `Screen` elements to observe the beam, and additional GPSR functionalities:"
    ]
   },
@@ -2616,7 +2609,9 @@
     }
    },
    "source": [
-    "GPSR model contains the beam NN generator and differentiable cheetah tracking lattice:"
+    "### GPSR Model \n",
+    "\n",
+    "contains the beam NN generator and differentiable cheetah tracking lattice:"
    ]
   },
   {
@@ -2642,7 +2637,8 @@
    "source": [
     "Due to the full PyTorch implementation, GPSR can make use of:\n",
     "- PyTorch `DataLoader`\n",
-    "- PyTorch Lightining, a package that provides a high level interface to train PyTorch models."
+    "- PyTorch Lightining, a package that provides a high level interface to train PyTorch models.\n",
+    "- GPU hardware acceleration (if available)"
    ]
   },
   {
@@ -2678,7 +2674,7 @@
     }
    },
    "source": [
-    "Lightning selects a GPU (if available), and does the training of the GPSR model:"
+    "### Training"
    ]
   },
   {
@@ -2743,7 +2739,9 @@
     }
    },
    "source": [
-    "We can look at the results by looking at the predicted and measured screen images for the scan parameters"
+    "### Results\n",
+    "\n",
+    "Predicted and measured screen images for the scan parameters"
    ]
   },
   {
@@ -2786,7 +2784,9 @@
     }
    },
    "source": [
-    "Cheetah has a useful plotting routines to see the 2D projections of the 6D beam distributions:"
+    "### Results\n",
+    "\n",
+    "2D projections of the reconstructied 6D phase space distributions:"
    ]
   },
   {
@@ -2814,13 +2814,6 @@
     "reconstructed_beam = litgpsr.gpsr_model.beam_generator()\n",
     "reconstructed_beam.plot_distribution();"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
diff --git a/tutorial.slides.html b/tutorial.slides.html
@@ -9820,8 +9820,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>Diagnostics for generative phase space reconstruction (GPSR)</p>
-<p><img alt="No description has been provided for this image" src="fig/gpsr_scan.png" style="width:90%; margin:auto;"/></p>
+<h3 id="Diagnostics-for-generative-phase-space-reconstruction-(GPSR)">Diagnostics for generative phase space reconstruction (GPSR)<a class="anchor-link" href="#Diagnostics-for-generative-phase-space-reconstruction-(GPSR)">¶</a></h3><p><img alt="No description has been provided for this image" src="fig/gpsr_scan.png" style="width:90%; margin:auto;"/></p>
 </div>
 </div>
 </div>
@@ -9832,7 +9831,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>Load example GPSR dataset</p>
+<h3 id="Example-GPSR-Dataset">Example GPSR Dataset<a class="anchor-link" href="#Example-GPSR-Dataset">¶</a></h3>
 </div>
 </div>
 </div>
@@ -9863,25 +9862,14 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 </div>
 </div>
-</div></div><div class="fragment">
-<div class="jp-Cell jp-MarkdownCell jp-Notebook-cell">
-<div class="jp-Cell-inputWrapper" tabindex="0">
-<div class="jp-Collapser jp-InputCollapser jp-Cell-inputCollapser">
-</div>
-<div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
-</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-</div>
-</div>
-</div>
 </div></div></section></section><section><section>
 <div class="jp-Cell jp-MarkdownCell jp-Notebook-cell">
 <div class="jp-Cell-inputWrapper" tabindex="0">
 <div class="jp-Collapser jp-InputCollapser jp-Cell-inputCollapser">
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>Let's inspect the GPSR dataset.</p>
-<p>The dataset is a custom PyTorch <code>Dataset</code>:</p>
+<h3 id="Let's-inspect-the-GPSR-dataset.">Let's inspect the GPSR dataset.<a class="anchor-link" href="#Let's-inspect-the-GPSR-dataset.">¶</a></h3><p>The dataset is a custom PyTorch <code>Dataset</code>:</p>
 </div>
 </div>
 </div>
@@ -9890,11 +9878,11 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 <div class="jp-Collapser jp-InputCollapser jp-Cell-inputCollapser">
 </div>
 <div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [38]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [50]:</div>
 <div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
 <div class="cm-editor cm-s-jupyter">
-<div class="highlight hl-ipython3"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'gpsr dataset class: </span><span class="si">{</span><span class="n">obs_dataset</span><span class="o">.</span><span class="vm">__class__</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
-<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'gpsr dataset parent class: </span><span class="si">{</span><span class="n">obs_dataset</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__bases__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="vm">__bases__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
+<div class="highlight hl-ipython3"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="n">obs_dataset</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
+<span class="nb">print</span><span class="p">(</span><span class="n">obs_dataset</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__bases__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="vm">__bases__</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
 </pre></div>
 </div>
 </div>
@@ -9907,8 +9895,8 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 <div class="jp-OutputArea-child">
 <div class="jp-OutputPrompt jp-OutputArea-prompt"></div>
 <div class="jp-RenderedText jp-OutputArea-output" data-mime-type="text/plain" tabindex="0">
-<pre>gpsr dataset class: &lt;class 'gpsr.datasets.SixDReconstructionDataset'&gt;
-gpsr dataset parent class: &lt;class 'torch.utils.data.dataset.Dataset'&gt;
+<pre>&lt;class 'gpsr.datasets.SixDReconstructionDataset'&gt;
+&lt;class 'torch.utils.data.dataset.Dataset'&gt;
 </pre>
 </div>
 </div>
@@ -9930,10 +9918,10 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 <div class="jp-Collapser jp-InputCollapser jp-Cell-inputCollapser">
 </div>
 <div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [39]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [51]:</div>
 <div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
 <div class="cm-editor cm-s-jupyter">
-<div class="highlight hl-ipython3"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'dataset parameters shape: </span><span class="si">{</span><span class="n">obs_dataset</span><span class="o">.</span><span class="n">six_d_params</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
+<div class="highlight hl-ipython3"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="n">obs_dataset</span><span class="o">.</span><span class="n">six_d_params</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
@@ -9946,7 +9934,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 <div class="jp-OutputArea-child">
 <div class="jp-OutputPrompt jp-OutputArea-prompt"></div>
 <div class="jp-RenderedText jp-OutputArea-output" data-mime-type="text/plain" tabindex="0">
-<pre>dataset parameters shape: torch.Size([2, 2, 5, 3])
+<pre>torch.Size([2, 2, 5, 3])
 </pre>
 </div>
 </div>
@@ -10050,7 +10038,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>Lattice creation is done using a wrapper class which contains the Cheetah <code>Segment</code> for tracking, the cheetah <code>Screen</code> elements to observe the beam, and additional GPSR functionalities:</p>
+<h3 id="GPSR-Diagnostics-Lattice">GPSR Diagnostics Lattice<a class="anchor-link" href="#GPSR-Diagnostics-Lattice">¶</a></h3><p>Lattice creation is done using a wrapper class which contains the Cheetah <code>Segment</code> for tracking, the cheetah <code>Screen</code> elements to observe the beam, and additional GPSR functionalities:</p>
 </div>
 </div>
 </div>
@@ -10182,7 +10170,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>GPSR model contains the beam NN generator and differentiable cheetah tracking lattice:</p>
+<h3 id="GPSR-Model">GPSR Model<a class="anchor-link" href="#GPSR-Model">¶</a></h3><p>contains the beam NN generator and differentiable cheetah tracking lattice:</p>
 </div>
 </div>
 </div>
@@ -10211,6 +10199,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 <ul>
 <li>PyTorch <code>DataLoader</code></li>
 <li>PyTorch Lightining, a package that provides a high level interface to train PyTorch models.</li>
+<li>GPU hardware acceleration (if available)</li>
 </ul>
 </div>
 </div>
@@ -10253,7 +10242,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>Lightning selects a GPU (if available), and does the training of the GPSR model:</p>
+<h3 id="Training">Training<a class="anchor-link" href="#Training">¶</a></h3>
 </div>
 </div>
 </div>
@@ -10316,7 +10305,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>We can look at the results by looking at the predicted and measured screen images for the scan parameters</p>
+<h3 id="Results">Results<a class="anchor-link" href="#Results">¶</a></h3><p>Predicted and measured screen images for the scan parameters</p>
 </div>
 </div>
 </div>
@@ -10361,7 +10350,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>Cheetah has a useful plotting routines to see the 2D projections of the 6D beam distributions:</p>
+<h3 id="Results">Results<a class="anchor-link" href="#Results">¶</a></h3><p>2D projections of the reconstructied 6D phase space distributions:</p>
 </div>
 </div>
 </div>
@@ -10393,20 +10382,6 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
 </div>
 </div>
 </div>
-</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs">
-<div class="jp-Cell-inputWrapper" tabindex="0">
-<div class="jp-Collapser jp-InputCollapser jp-Cell-inputCollapser">
-</div>
-<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [ ]:</div>
-<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
-<div class="cm-editor cm-s-jupyter">
-<div class="highlight hl-ipython3"><pre><span></span> 
-</pre></div>
-</div>
-</div>
-</div>
-</div>
 </div></div></section></section>
 </div>
 </div>
@@ -10447,7 +10422,7 @@ <h2 style="color: #b51f2a">Example 4: generative phase space reconstruction (10
         Reveal.addEventListener('slidechanged', update);
 
         function setScrollingSlide() {
-            var scroll = false
+            var scroll = true
             if (scroll === true) {
               var h = $('.reveal').height() * 0.95;
               $('section.present').find('section')

Original file line number	Diff line number	Diff line change
`@@ -2292,7 +2292,7 @@`
`2292`	`2292`	`}`
`2293`	`2293`	`},`
`2294`	`2294`	`"source": [`
`2295`		`- "Diagnostics for generative phase space reconstruction (GPSR)\n",`
	`2295`	`+ "### Diagnostics for generative phase space reconstruction (GPSR)\n",`
`2296`	`2296`	`"\n",`
`2297`	`2297`	`"<img src=\"fig/gpsr_scan.png\" style=\"width:90%; margin:auto;\"/>"`
`2298`	`2298`	`]`
`@@ -2305,7 +2305,7 @@`
`2305`	`2305`	`}`
`2306`	`2306`	`},`
`2307`	`2307`	`"source": [`
`2308`		`- "Load example GPSR dataset"`
	`2308`	`+ "### Example GPSR Dataset"`
`2309`	`2309`	`]`
`2310`	`2310`	`},`
`2311`	`2311`	`{`
`@@ -2333,15 +2333,6 @@`
`2333`	`2333`	`"obs_dataset.plot_data(publication_size=True);"`
`2334`	`2334`	`]`
`2335`	`2335`	`},`
`2336`		`- {`
`2337`		`- "cell_type": "markdown",`
`2338`		`- "metadata": {`
`2339`		`- "slideshow": {`
`2340`		`- "slide_type": "fragment"`
`2341`		`- }`
`2342`		`- },`
`2343`		`- "source": []`
`2344`		`- },`
`2345`	`2336`	`{`
`2346`	`2337`	`"cell_type": "markdown",`
`2347`	`2338`	`"metadata": {`
`@@ -2350,14 +2341,14 @@`
`2350`	`2341`	`}`
`2351`	`2342`	`},`
`2352`	`2343`	`"source": [`
`2353`		`- "Let's inspect the GPSR dataset.\n",`
	`2344`	`+ "### Let's inspect the GPSR dataset.\n",`
`2354`	`2345`	`"\n",`
`2355`	`2346`	"The dataset is a custom PyTorch `Dataset`:"
`2356`	`2347`	`]`
`2357`	`2348`	`},`
`2358`	`2349`	`{`
`2359`	`2350`	`"cell_type": "code",`
`2360`		`- "execution_count": 38,`
	`2351`	`+ "execution_count": 50,`
`2361`	`2352`	`"metadata": {`
`2362`	`2353`	`"slideshow": {`
`2363`	`2354`	`"slide_type": "fragment"`
`@@ -2368,14 +2359,14 @@`
`2368`	`2359`	`"name": "stdout",`
`2369`	`2360`	`"output_type": "stream",`
`2370`	`2361`	`"text": [`
`2371`		`- "gpsr dataset class: <class 'gpsr.datasets.SixDReconstructionDataset'>\n",`
`2372`		`- "gpsr dataset parent class: <class 'torch.utils.data.dataset.Dataset'>\n"`
	`2362`	`+ "<class 'gpsr.datasets.SixDReconstructionDataset'>\n",`
	`2363`	`+ "<class 'torch.utils.data.dataset.Dataset'>\n"`
`2373`	`2364`	`]`
`2374`	`2365`	`}`
`2375`	`2366`	`],`
`2376`	`2367`	`"source": [`
`2377`		`- "print(f'gpsr dataset class: {obs_dataset.__class__}')\n",`
`2378`		`- "print(f'gpsr dataset parent class: {obs_dataset.__class__.__bases__[0].__bases__[0]}')"`
	`2368`	`+ "print(obs_dataset.__class__)\n",`
	`2369`	`+ "print(obs_dataset.__class__.__bases__[0].__bases__[0])"`
`2379`	`2370`	`]`
`2380`	`2371`	`},`
`2381`	`2372`	`{`
`@@ -2391,7 +2382,7 @@`
`2391`	`2382`	`},`
`2392`	`2383`	`{`
`2393`	`2384`	`"cell_type": "code",`
`2394`		`- "execution_count": 39,`
	`2385`	`+ "execution_count": 51,`
`2395`	`2386`	`"metadata": {`
`2396`	`2387`	`"slideshow": {`
`2397`	`2388`	`"slide_type": "fragment"`
`@@ -2402,12 +2393,12 @@`
`2402`	`2393`	`"name": "stdout",`
`2403`	`2394`	`"output_type": "stream",`
`2404`	`2395`	`"text": [`
`2405`		`- "dataset parameters shape: torch.Size([2, 2, 5, 3])\n"`
	`2396`	`+ "torch.Size([2, 2, 5, 3])\n"`
`2406`	`2397`	`]`
`2407`	`2398`	`}`
`2408`	`2399`	`],`
`2409`	`2400`	`"source": [`
`2410`		`- "print(f'dataset parameters shape: {obs_dataset.six_d_params.shape}')"`
	`2401`	`+ "print(obs_dataset.six_d_params.shape)"`
`2411`	`2402`	`]`
`2412`	`2403`	`},`
`2413`	`2404`	`{`
`@@ -2497,6 +2488,8 @@`
`2497`	`2488`	`}`
`2498`	`2489`	`},`
`2499`	`2490`	`"source": [`
	`2491`	`+ "### GPSR Diagnostics Lattice\n",`
	`2492`	`+ "\n",`
`2500`	`2493`	"Lattice creation is done using a wrapper class which contains the Cheetah `Segment` for tracking, the cheetah `Screen` elements to observe the beam, and additional GPSR functionalities:"
`2501`	`2494`	`]`
`2502`	`2495`	`},`
`@@ -2616,7 +2609,9 @@`
`2616`	`2609`	`}`
`2617`	`2610`	`},`
`2618`	`2611`	`"source": [`
`2619`		`- "GPSR model contains the beam NN generator and differentiable cheetah tracking lattice:"`
	`2612`	`+ "### GPSR Model \n",`
	`2613`	`+ "\n",`
	`2614`	`+ "contains the beam NN generator and differentiable cheetah tracking lattice:"`
`2620`	`2615`	`]`
`2621`	`2616`	`},`
`2622`	`2617`	`{`
`@@ -2642,7 +2637,8 @@`
`2642`	`2637`	`"source": [`
`2643`	`2638`	`"Due to the full PyTorch implementation, GPSR can make use of:\n",`
`2644`	`2639`	"- PyTorch `DataLoader`\n",
`2645`		`- "- PyTorch Lightining, a package that provides a high level interface to train PyTorch models."`
	`2640`	`+ "- PyTorch Lightining, a package that provides a high level interface to train PyTorch models.\n",`
	`2641`	`+ "- GPU hardware acceleration (if available)"`
`2646`	`2642`	`]`
`2647`	`2643`	`},`
`2648`	`2644`	`{`
`@@ -2678,7 +2674,7 @@`
`2678`	`2674`	`}`
`2679`	`2675`	`},`
`2680`	`2676`	`"source": [`
`2681`		`- "Lightning selects a GPU (if available), and does the training of the GPSR model:"`
	`2677`	`+ "### Training"`
`2682`	`2678`	`]`
`2683`	`2679`	`},`
`2684`	`2680`	`{`
`@@ -2743,7 +2739,9 @@`
`2743`	`2739`	`}`
`2744`	`2740`	`},`
`2745`	`2741`	`"source": [`
`2746`		`- "We can look at the results by looking at the predicted and measured screen images for the scan parameters"`
	`2742`	`+ "### Results\n",`
	`2743`	`+ "\n",`
	`2744`	`+ "Predicted and measured screen images for the scan parameters"`
`2747`	`2745`	`]`
`2748`	`2746`	`},`
`2749`	`2747`	`{`
`@@ -2786,7 +2784,9 @@`
`2786`	`2784`	`}`
`2787`	`2785`	`},`
`2788`	`2786`	`"source": [`
`2789`		`- "Cheetah has a useful plotting routines to see the 2D projections of the 6D beam distributions:"`
	`2787`	`+ "### Results\n",`
	`2788`	`+ "\n",`
	`2789`	`+ "2D projections of the reconstructied 6D phase space distributions:"`
`2790`	`2790`	`]`
`2791`	`2791`	`},`
`2792`	`2792`	`{`
`@@ -2814,13 +2814,6 @@`
`2814`	`2814`	`"reconstructed_beam = litgpsr.gpsr_model.beam_generator()\n",`
`2815`	`2815`	`"reconstructed_beam.plot_distribution();"`
`2816`	`2816`	`]`
`2817`		`- },`
`2818`		`- {`
`2819`		`- "cell_type": "code",`
`2820`		`- "execution_count": null,`
`2821`		`- "metadata": {},`
`2822`		`- "outputs": [],`
`2823`		`- "source": []`
`2824`	`2817`	`}`
`2825`	`2818`	`],`
`2826`	`2819`	`"metadata": {`