diff options
Diffstat (limited to 'docs/posts/2019-12-08-Image-Classifier-Tensorflow.html')
| -rw-r--r-- | docs/posts/2019-12-08-Image-Classifier-Tensorflow.html | 28 |
1 files changed, 14 insertions, 14 deletions
diff --git a/docs/posts/2019-12-08-Image-Classifier-Tensorflow.html b/docs/posts/2019-12-08-Image-Classifier-Tensorflow.html index 4d27f40..a5f7ef9 100644 --- a/docs/posts/2019-12-08-Image-Classifier-Tensorflow.html +++ b/docs/posts/2019-12-08-Image-Classifier-Tensorflow.html @@ -6,13 +6,13 @@ <link rel="stylesheet" href="/assets/main.css" /> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> - <title>Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria</title> + <title>id="creating-a-custom-image-classifier-using-tensorflow-2x-and-keras-for-detecting-malaria">Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria</title> <meta name="og:site_name" content="Navan Chauhan" /> <link rel="canonical" href="https://web.navan.dev/posts/2019-12-08-Image-Classifier-Tensorflow.html" /> <meta name="twitter:url" content="https://web.navan.dev/posts/2019-12-08-Image-Classifier-Tensorflow.html /> <meta name="og:url" content="https://web.navan.dev/posts/2019-12-08-Image-Classifier-Tensorflow.html" /> - <meta name="twitter:title" content="Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria" /> - <meta name="og:title" content="Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria" /> + <meta name="twitter:title" content="id="creating-a-custom-image-classifier-using-tensorflow-2x-and-keras-for-detecting-malaria">Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria" /> + <meta name="og:title" content="id="creating-a-custom-image-classifier-using-tensorflow-2x-and-keras-for-detecting-malaria">Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria" /> <meta name="description" content="Tutorial on creating an image classifier model using TensorFlow which detects malaria" /> <meta name="twitter:description" content="Tutorial on creating an image classifier model using TensorFlow which detects malaria" /> <meta name="og:description" content="Tutorial on creating an image classifier model using TensorFlow which detects malaria" /> @@ -44,11 +44,11 @@ <main> - <h1>Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria</h1> + <h1 id="creating-a-custom-image-classifier-using-tensorflow-2x-and-keras-for-detecting-malaria">Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria</h1> <p><strong>Done during Google Code-In. Org: Tensorflow.</strong></p> -<h2>Imports</h2> +<h2 id="imports">Imports</h2> <div class="codehilite"> <pre><span></span><code><span class="o">%</span><span class="n">tensorflow_version</span> <span class="mf">2.</span><span class="n">x</span> <span class="c1">#This is for telling Colab that you want to use TF 2.0, ignore if running on local machine</span> @@ -66,9 +66,9 @@ </code></pre> </div> -<h2>Dataset</h2> +<h2 id="dataset">Dataset</h2> -<h3>Fetching the Data</h3> +<h3 id="fetching-the-data">Fetching the Data</h3> <div class="codehilite"> <pre><span></span><code><span class="err">!</span><span class="n">wget</span> <span class="n">ftp</span><span class="p">:</span><span class="o">//</span><span class="n">lhcftp</span><span class="o">.</span><span class="n">nlm</span><span class="o">.</span><span class="n">nih</span><span class="o">.</span><span class="n">gov</span><span class="o">/</span><span class="n">Open</span><span class="o">-</span><span class="n">Access</span><span class="o">-</span><span class="n">Datasets</span><span class="o">/</span><span class="n">Malaria</span><span class="o">/</span><span class="n">cell_images</span><span class="o">.</span><span class="n">zip</span> @@ -76,7 +76,7 @@ </code></pre> </div> -<h3>Processing the Data</h3> +<h3 id="processing-the-data">Processing the Data</h3> <p>We resize all the images as 50x50 and add the numpy array of that image as well as their label names (Infected or Not) to common arrays.</p> @@ -108,7 +108,7 @@ </code></pre> </div> -<h3>Splitting Data</h3> +<h3 id="splitting-data">Splitting Data</h3> <div class="codehilite"> <pre><span></span><code><span class="n">df</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> @@ -125,9 +125,9 @@ y_train=y_train[s] X_train = X_train/255.0 </code></pre> -<h2>Model</h2> +<h2 id="model">Model</h2> -<h3>Creating Model</h3> +<h3 id="creating-model">Creating Model</h3> <p>By creating a sequential model, we create a linear stack of layers.</p> @@ -150,7 +150,7 @@ X_train = X_train/255.0 </code></pre> </div> -<h3>Compiling Model</h3> +<h3 id="compiling-model">Compiling Model</h3> <p>We use the Adam optimiser as it is an adaptive learning rate optimisation algorithm that's been designed specifically for <em>training</em> deep neural networks, which means it changes its learning rate automatically to get the best results</p> @@ -161,7 +161,7 @@ X_train = X_train/255.0 </code></pre> </div> -<h3>Training Model</h3> +<h3 id="training-model">Training Model</h3> <p>We train the model for 10 epochs on the training data and then validate it using the testing data</p> @@ -195,7 +195,7 @@ X_train = X_train/255.0 </code></pre> </div> -<h3>Results</h3> +<h3 id="results">Results</h3> <div class="codehilite"> <pre><span></span><code><span class="n">accuracy</span> <span class="o">=</span> <span class="n">history</span><span class="o">.</span><span class="n">history</span><span class="p">[</span><span class="s1">'accuracy'</span><span class="p">][</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">*</span><span class="mi">100</span> |