Deploying the Model
The model would be deployed using Binder. The GitHub URL of the notebook needs to be pasted. Firstly, the model needs to be exported, and a file with the extension .pkl needs to be generated.
Python3
learn.export() path = Path() path.ls(file_exts = '.pkl' ) |
Visit the website for Binder. Paste the URL of the GitHub repository, containing the notebook and .pkl file. In the ‘URL to open’ blank, enter the (GitHub) URL of the notebook. Click on ‘launch’, and after a few minutes, the web-application would be ready to be used.
Note: This image classifier was first taught in the Fast.AI Deep Learning course, lecture 2.
Identify Members of BTS — An Image Classifier
BTS is an eminent K-Pop band comprising of 7 members. This article looks at an image classifier that would recognize the name of the band member from a picture. The image classifier would be built using fastai. It is a deep learning library that aims to democratize deep learning. It is built on top of PyTorch, and has plethora of models with optimized weights that are ready-to-use. The application would be hosted on Binder, and the end product would look like this: