Concept | Pre-trained image classification models#

What are pre-trained models?#

In many computer vision tasks, you will come across pre-trained models. Pre-trained models are useful for dealing with classification tasks, among others. Perhaps you’ve already tried to build your own convolutional neural network (or CNN) to classify lower-dimensional images, letters, or digits. For lower-dimensional images, a simple CNN architecture will suffice.

../../_images/pretrained-model-summ1.png

Now let’s say you are trying to classify more complex images, which are made up of many colors, oriented in different positions, or which exhibit other novel behavior. At this point, you might not want to build a model from scratch, as doing so would require a lot of data, resources, and a complex architecture.

Instead, you could begin with a pre-trained model, a more complex CNN that has been trained on huge datasets and can predict various classes. You can finetune this pre-trained model on your data by identifying the layers of the neural network that need to be retrained on your data.

../../_images/pretrained-model-summ2.png

Pre-trained models in Dataiku#

Dataiku’s image classification feature includes three pre-trained networks that are widely used and considered industry standards. The models offer a range of efficiency and performance:

  • EfficientNet B0: Efficiency-oriented

  • EfficientNet B4: Balanced between efficiency and performance

  • EfficientNet B7: Performance-oriented