Cat v/s Dog classifier using transfer learning with MobileNet INTRODUCTION: TRANSFER LEARNING
Transfer learning allows us to train deep networks using significantly less data then we would need if we had to train from scratch. With transfer learning, we are in effect transferring the “knowledge” that a model has learned from a previous task, to our current one. The idea is that the two tasks are not totally disjoint, and as such we can leverage whatever network parameters that model has learned through its extensive training, without having to do that training ourselves.
Transfer learning has been consistently proven to boost model accuracy and reduce require training time. Less data, less time, more accuracy. My model can classify Cats and Dogs and had achieved validation accuracy as ~94%.
Following are the dependencies and their installation commands:
- Keras
conda install -c conda-forge keras - OpenCV
conda install -c conda-forge opencv - Numpy
conda install -c anaconda numpy