Learn how to do multiclass classification and use custom datasets in Keras. The reader is assumed to be proficient with basics of machine learning, especially the reader should know how to use appropriate activation function at the readout layer.
The post explains the following
- The problem statement in hand
- How to use custom datasets and appropriately preprocess it using glob module.
- Designing the Architecture of the network
- Training the network using Keras
The tutorial is available below:
Follow @brobear1995 for more such posts!
You may also like:
Introduction to Automatic Image Captioning
Congratulations @brobear1995! You have completed some achievement on Steemit and have been rewarded with new badge(s) :
Click on any badge to view your own Board of Honor on SteemitBoard.
For more information about SteemitBoard, click here
If you no longer want to receive notifications, reply to this comment with the word
STOPDownvoting a post can decrease pending rewards and make it less visible. Common reasons:
Submit
Thanks, great and simple tutorial! Seems to me it can be improved with more training examples and I might add that for production dlib's face detector is a bit slow. Also it would be nice to see how the system performs extracting facial features with dlib.shape_predictor.
Downvoting a post can decrease pending rewards and make it less visible. Common reasons:
Submit