A large number of problems in the computer vision domain can be solved using image classification approaches. These include building models which answer questions such as, "Is an OBJECT present in the image?" (where OBJECT could for example be "dog", "car", "ship", etc.) as well as more complex questions, like "What class of eye disease is evinced by this patient's retinal scan?" This solution will address solving such problems. We will show how to train, evaluate and deploy your own image classification model using the Microsoft Cognitive Toolkit (CNTK) for deep learning. Example images are provided, but the reader can also bring their own dataset and train their own custom models. The key steps required to deliver this solution are as follows: 1. Generate an annotated image dataset. Alternatively, the provided demo dataset can be used. 2. Train an image classifier using a pre-trained Deep Neural Network. 3. Evaluate and improve accuracy of this model. 4. Deploy the model as a REST API, either to the local machine or to the cloud.
- The detailed documentation for this image classification solution including step-by-step instructions: [https://docs.microsoft.com/azure/machine-learning/preview/scenario-image-classification-using-cntk]. - All code for this solution can be found by clicking the View Project icon on the right which will open the project GitHub repository. - Key components needed to run this example: 1. An Azure account (free trials are available). 2. An installed copy of Azure Machine Learning Workbench with a workspace created. 3. A machine or VM running Windows. 4. A dedicated GPU is recommended, however not required. : https://docs.microsoft.com/azure/machine-learning/preview/scenario-image-classification-using-cntk