Pocket AutoML

Evgeniy Mamchenko

O aplikaciji

• Pocket AutoML lets artificial intelligence enthusiasts even without prior machine learning experience train a deep learning image classification model (a convolutional neural network) right on their devices and experiment with it.
• It can export models it in TensorFlow Lite format so a user can make a custom Android app based on it following the provided tutorial.
• Computer vision or deep learning professionals can also use it as a tool to create a quick proof-of-concept for transfer learning on their tasks without a single line of code.
• It trains a model right on on your device in seconds (for a dataset with dozens of images).
• It respects your privacy: your images are never uploaded anywhere as both training and prediction happens on your device.
• It does not need an internet connection for training and predicting.
• Just few images per class can be enough to train a model that accurately classifies objects (what is known as few-shot learning).

Što je novo

• Improved model training speed.
• Added the Android app creation tutorial.
• Added model export in TensorFlow Lite format.
• Added model statistics.
• Fixed an issue with the app returning to the main screen, e.g. when taking or picking photos.
• Better photo quality.
• More hints for new users.
• Faster image import from device storage.
• Other bugfixes and improvements.