deploy: ec94fe2

geo-smart · Nov 25, 2024 · 4294dd6 · 4294dd6
1 parent de57935
commit 4294dd6
Show file tree

Hide file tree

Showing 21 changed files with 765 additions and 375 deletions.
diff --git a/Chapter4-DeepLearning/mlgeo_4.4_RNN.html b/Chapter4-DeepLearning/mlgeo_4.4_RNN.html
diff --git a/Chapter4-DeepLearning/mlgeo_4.6_AutoEncoder.html b/Chapter4-DeepLearning/mlgeo_4.6_AutoEncoder.html
@@ -809,6 +809,48 @@ <h1>4.6 Auto-encoders<a class="headerlink" href="#auto-encoders" title="Permalin
 </pre></div>
 </div>
 </div>
+<div class="cell_output docutils container">
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ./FashionMNIST/raw/train-images-idx3-ubyte.gz
+</pre></div>
+</div>
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|██████████| 26421880/26421880 [00:02&lt;00:00, 10417165.17it/s]
+</pre></div>
+</div>
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Extracting ./FashionMNIST/raw/train-images-idx3-ubyte.gz to ./FashionMNIST/raw
+
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to ./FashionMNIST/raw/train-labels-idx1-ubyte.gz
+</pre></div>
+</div>
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|██████████| 29515/29515 [00:00&lt;00:00, 175578.14it/s]
+</pre></div>
+</div>
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Extracting ./FashionMNIST/raw/train-labels-idx1-ubyte.gz to ./FashionMNIST/raw
+
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to ./FashionMNIST/raw/t10k-images-idx3-ubyte.gz
+</pre></div>
+</div>
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|██████████| 4422102/4422102 [00:01&lt;00:00, 3538808.13it/s]
+</pre></div>
+</div>
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Extracting ./FashionMNIST/raw/t10k-images-idx3-ubyte.gz to ./FashionMNIST/raw
+
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to ./FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
+</pre></div>
+</div>
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|██████████| 5148/5148 [00:00&lt;00:00, 8317518.10it/s]
+</pre></div>
+</div>
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Extracting ./FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to ./FashionMNIST/raw
+</pre></div>
+</div>
+<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>
+</pre></div>
+</div>
+</div>
 </div>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
@@ -820,8 +862,7 @@ <h1>4.6 Auto-encoders<a class="headerlink" href="#auto-encoders" title="Permalin
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&lt;torch.utils.data.dataset.Subset object at 0x2af90f8b0&gt;
-torch.Size([50, 1, 28, 28])
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>torch.Size([50, 1, 28, 28])
 </pre></div>
 </div>
 </div>
@@ -1005,11 +1046,11 @@ <h1>4.6 Auto-encoders<a class="headerlink" href="#auto-encoders" title="Permalin
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[Epoch 1] train loss: 0.596 - val loss: 0.594
-[Epoch 2] train loss: 0.596 - val loss: 0.593
-[Epoch 3] train loss: 0.595 - val loss: 0.593
-[Epoch 4] train loss: 0.595 - val loss: 0.593
-[Epoch 5] train loss: 0.595 - val loss: 0.593
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[Epoch 1] train loss: 0.617 - val loss: 0.603
+[Epoch 2] train loss: 0.599 - val loss: 0.599
+[Epoch 3] train loss: 0.596 - val loss: 0.597
+[Epoch 4] train loss: 0.595 - val loss: 0.597
+[Epoch 5] train loss: 0.595 - val loss: 0.596
 </pre></div>
 </div>
 </div>
@@ -1023,7 +1064,7 @@ <h1>4.6 Auto-encoders<a class="headerlink" href="#auto-encoders" title="Permalin
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[&lt;matplotlib.lines.Line2D at 0x2d0523130&gt;]
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[&lt;matplotlib.lines.Line2D at 0x3154edbb0&gt;]
 </pre></div>
 </div>
 <img alt="../_images/mlgeo_4.6_AutoEncoder_11_1.png" src="../_images/mlgeo_4.6_AutoEncoder_11_1.png" />
@@ -1141,11 +1182,11 @@ <h1>Convolutional autoencoder<a class="headerlink" href="#convolutional-autoenco
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[Epoch 1] train loss: 0.609 - val loss: 0.574
-[Epoch 2] train loss: 0.574 - val loss: 0.571
-[Epoch 3] train loss: 0.572 - val loss: 0.570
-[Epoch 4] train loss: 0.571 - val loss: 0.569
-[Epoch 5] train loss: 0.571 - val loss: 0.569
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[Epoch 1] train loss: 0.611 - val loss: 0.578
+[Epoch 2] train loss: 0.574 - val loss: 0.574
+[Epoch 3] train loss: 0.572 - val loss: 0.573
+[Epoch 4] train loss: 0.571 - val loss: 0.573
+[Epoch 5] train loss: 0.571 - val loss: 0.572
 </pre></div>
 </div>
 </div>
@@ -1176,7 +1217,7 @@ <h1>Denoising auto-encoder<a class="headerlink" href="#denoising-auto-encoder" t
 
         <span class="c1"># Encoder</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">encoder</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
-            <span class="n">nn</span><span class="o">.</span><span class="n">DropOut</span><span class="p">(</span><span class="mf">0.2</span><span class="p">),</span> <span class="c1">#  Dropout layer to mimic noisy data</span>
+            <span class="n">nn</span><span class="o">.</span><span class="n">Dropout</span><span class="p">(</span><span class="mf">0.2</span><span class="p">),</span> <span class="c1">#  Dropout layer to mimic noisy data</span>
             <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">16</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
             <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
             <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">16</span><span class="p">,</span> <span class="mi">32</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
@@ -1198,70 +1239,23 @@ <h1>Denoising auto-encoder<a class="headerlink" href="#denoising-auto-encoder" t
 </pre></div>
 </div>
 </div>
-<div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Model: &quot;sequential_15&quot;
-_________________________________________________________________
-Layer (type)                 Output Shape              Param #   
-=================================================================
-encoder_cnn (Sequential)     (None, 3, 3, 64)          23296     
-_________________________________________________________________
-decoder_cnn (Sequential)     (None, 28, 28)            23233     
-=================================================================
-Total params: 46,529
-Trainable params: 46,529
-Non-trainable params: 0
-_________________________________________________________________
+</div>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Instantiate the model</span>
+<span class="n">model_denoised_CNNAE</span> <span class="o">=</span> <span class="n">DenoiseCNNAE</span><span class="p">()</span>
 </pre></div>
 </div>
 </div>
 </div>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="p">(</span><span class="n">loss</span><span class="p">,</span> <span class="n">loss_val</span><span class="p">)</span> <span class="o">=</span> <span class="n">train</span><span class="p">(</span><span class="n">DenoiseCNNAE</span><span class="p">,</span> <span class="mi">30</span><span class="p">,</span><span class="n">loaded_train</span><span class="p">,</span> <span class="n">loaded_test</span><span class="p">)</span>
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="p">(</span><span class="n">loss</span><span class="p">,</span> <span class="n">loss_val</span><span class="p">)</span> <span class="o">=</span> <span class="n">train</span><span class="p">(</span><span class="n">model_denoised_CNNAE</span><span class="p">,</span> <span class="mi">30</span><span class="p">,</span><span class="n">loaded_train</span><span class="p">,</span> <span class="n">loaded_test</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch 1/20
-1719/1719 [==============================] - 25s 14ms/step - loss: 0.2551 - val_loss: 0.2533
-Epoch 2/20
-1719/1719 [==============================] - 26s 15ms/step - loss: 0.2565 - val_loss: 0.2543
-Epoch 3/20
-1719/1719 [==============================] - 26s 15ms/step - loss: 0.2554 - val_loss: 0.2525
-Epoch 4/20
-1719/1719 [==============================] - 25s 14ms/step - loss: 0.2551 - val_loss: 0.2531
-Epoch 5/20
-1719/1719 [==============================] - 26s 15ms/step - loss: 0.2557 - val_loss: 0.2524
-Epoch 6/20
-1719/1719 [==============================] - 27s 16ms/step - loss: 0.2550 - val_loss: 0.2526
-Epoch 7/20
-1719/1719 [==============================] - 26s 15ms/step - loss: 0.2552 - val_loss: 0.2539
-Epoch 8/20
-1719/1719 [==============================] - 26s 15ms/step - loss: 0.2549 - val_loss: 0.2521
-Epoch 9/20
-1719/1719 [==============================] - 26s 15ms/step - loss: 0.2558 - val_loss: 0.2527
-Epoch 10/20
-1719/1719 [==============================] - 25s 15ms/step - loss: 0.2552 - val_loss: 0.2524
-Epoch 11/20
-1719/1719 [==============================] - 25s 15ms/step - loss: 0.2548 - val_loss: 0.2525
-Epoch 12/20
-1719/1719 [==============================] - 25s 15ms/step - loss: 0.2564 - val_loss: 0.2523
-Epoch 13/20
-1719/1719 [==============================] - 23s 13ms/step - loss: 0.2556 - val_loss: 0.2522
-Epoch 14/20
-1719/1719 [==============================] - 23s 13ms/step - loss: 0.2550 - val_loss: 0.2520
-Epoch 15/20
-1719/1719 [==============================] - 23s 13ms/step - loss: 0.2550 - val_loss: 0.2524
-Epoch 16/20
-1719/1719 [==============================] - 23s 13ms/step - loss: 0.2553 - val_loss: 0.2526
-Epoch 17/20
-1719/1719 [==============================] - 23s 13ms/step - loss: 0.2541 - val_loss: 0.2533
-Epoch 18/20
-1719/1719 [==============================] - 23s 14ms/step - loss: 0.2550 - val_loss: 0.2520
-Epoch 19/20
-1719/1719 [==============================] - 22s 13ms/step - loss: 0.2555 - val_loss: 0.2519
-Epoch 20/20
-1719/1719 [==============================] - 23s 13ms/step - loss: 0.2550 - val_loss: 0.2540
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[Epoch 1] train loss: 0.612 - val loss: 0.585
 </pre></div>
 </div>
 </div>
@@ -1273,7 +1267,7 @@ <h1>Denoising auto-encoder<a class="headerlink" href="#denoising-auto-encoder" t
 </div>
 </div>
 <div class="cell_output docutils container">
-<img alt="../_images/mlgeo_4.6_AutoEncoder_24_0.png" src="../_images/mlgeo_4.6_AutoEncoder_24_0.png" />
+<img alt="../_images/mlgeo_4.6_AutoEncoder_25_0.png" src="../_images/mlgeo_4.6_AutoEncoder_25_0.png" />
 </div>
 </div>
 </section>