In the development phase, you can use your test data to infer the species from an image that the model has not previously seen. This can be achieved by also using the build-in prediction tools in fast.ai as illustrated in the model inference section of the development phase. Whereas model training requires the use of Graphical Processing Units (GPUs) to quickly carry out the matrix multiplications that are implicit to AI models inference can be easily achieved using the CPU - and hence in the code we turn to using CPU for model inference because it is cheaper and faster for that task.
Refer to #CODE BLOCKS 5,6,7 # on Jupyter Notebook