||The official integrated development environment (IDE) for Android app development.
||A dependency manager used here for iOS app development; for Swift and
Objective-C Cocoa projects to provide a standard format for managing
||A machine learning framework used in Apple products. TensorFlow lite models
can be converted to CoreML format for use on Apple devices.
|Container ("export to Docker/container")
||The runtime instance of an image; one of the export options for your model
using AutoML Vision Edge.
||A device that provides compute capability outside the cloud. The demand for
privacy/confidentiality, low latency and bandwidth constraints drive demand for
predictions with our models on these devices. Compute and power
constraints lead to models specialized for them.
||A type of Edge device; Google's purpose-built application-specific integrated
circuit (ASIC) designed to run inference at the edge.
.tflite models only.
||A mobile and web application development platform.
||Similar to Protocol buffers, with the primary difference being that FlatBuffers
do not need a parsing/ unpacking step to a secondary representation before you
can access data, often coupled with per-object memory allocation.
||Internet of Things (IoT); the use of network-connected devices, embedded in
the physical environment, to improve some existing process or to enable a
new scenario not previously possible.
||ML Kit acts as an API layer to your custom model; a mobile software
development kit (SDK) that allows you to use a custom model on-device.
||The Python Imaging Library (PIL) adds image processing capabilities to your
Python interpreter; Pillow is a modified version of the base PIL.
|Protocol buffers ("protobuf")
||Google's language-neutral, platform-neutral, extensible mechanism for
serializing structured data. Similar to FlatBuffers.
||TensorFlow is an end-to-end open source platform for machine learning;
software used to create a machine learning model.
|TensorFlow lite model (TF Lite/
|A TensorFlow ML model that has been compressed for use on mobile and embedded
- TF Lite converter
- TensorFlow Lite uses the optimized FlatBuffer format to represent
graphs. Therefore, a TensorFlow model (protocol buffer) needs to be
converted into a FlatBuffer file before deploying to clients.
- TF Lite interpreter
- A class that does the job of a
tf.Session(), only for TF Lite
models as opposed to regular TensorFlow models.
|A class for running TensorFlow operations using a TensorFlow model.
||Xcode is an integrated development environment (IDE) for macOS containing
a suite of software development tools developed by Apple for developing
software for macOS, iOS, watchOS, and tvOS.