How to create a transfer learning model

<p>In&nbsp;<strong>convolutional neural networks,</strong>&nbsp;to reach the best accuracy and generalization ability, we need to test many experiments, adding layers or hidden units and so on. Sometimes it will take a lot of time and it can be just a random guess.</p> <p>But one thing is for sure,&nbsp;<strong>neural network</strong>&nbsp;is not a brand-new thing. Surely someone must have done the work and built a workable neural network model for specific problems. And there it is!</p> <p>So what if we use the model trained by other professionals and apply it on our own problem? That is what&nbsp;<strong>Transfer Learning</strong>&nbsp;does.</p> <p>&nbsp;</p> <p><em>Illustration from (zero to mastery course)</em></p> <p>Transfer learning can help us:</p> <ul> <li>Leverage an existing trained model that has been proven to work &mdash; save time</li> <li>Leverage a model that has already learned patterns on problems that we&rsquo;re working on.</li> </ul> <p>How to find available model structures and how to use them? Here I introduce two methods. In this blog, I take&nbsp;<strong>image domain</strong>&nbsp;and&nbsp;<strong>EfficientNetB0</strong>&nbsp;as an example of architecture.</p> <p>Before we start, let&rsquo;s assume that&nbsp;<strong>we are solving a computer vision problem</strong>.</p> <h1>Download the model from TensorFlow Hub</h1> <p>First, let&rsquo;s go to the [<a href="https://tfhub.dev/" rel="noopener ugc nofollow" target="_blank">TensorFlow Hub</a>]. On the homepage, we can see different types of problem domains.</p> <p><a href="https://medium.com/@719458145/how-to-create-a-transfer-learning-model-two-methods-1b9441a385e7">Website</a></p>