Get the code
View the demo
by Mark Studervant, Franck Barillaud | Published March 15, 2017
Artificial intelligenceData sciencePythonCloud
This code pattern was built for developers looking to leverage the new PowerAI offering from IBM. We will use a Jupyter Notebook to showcase an example of transfer learning with the TensorFlow Inception model on IBM POWER8® systems. The notebook will focus on creating a custom classifier to recognize houses with pools vs. houses without pools from JPEG images. The intended audience is application developers who need to efficiently build powerful deep-learning applications, but may not have an abundance of time or data science experience.
Transfer learning is the process of taking a pre-trained model (the weights and parameters of a network that has been trained on a large dataset by somebody else) and fine-tuning the model with your own dataset. The idea is that this pre-trained model will act as a feature extractor. You will remove the last layer of the network and replace it with your own classifier (depending on what your problem space is). You then freeze the weights of all the other layers (by not changing the weights during gradient descent/optimization) and train the network normally. For this experiment, we used the Inception-v3 pre-trained model for image classification. This model consists of two parts:
The pre-trained Inception-v3 model achieves state-of-the-art accuracy for recognizing general objects with 1,000 classes. The model extracts general features from input images in the first part and classifies them based on those features in the second part. We will use this pre-trained model and retrain it to classify houses with or without swimming pools.
Upon completion of this code pattern, you will understand how to load and run a Jupyter Notebook with Nimbix and PowerAI, use transfer learning to leverage the TensorFlow Inception model to create a custom classifier from a set of images, then test and demonstrate the resulting classifier.
Find the detailed steps for this pattern in the README. The steps will show you how to:
March 26, 2019
July 15, 2019
Adversarial Robustness ToolboxAI Fairness 360+
March 14, 2019
Back to top