Home
免费应用程序分析
ML Trainer: Make Training Data
ML Trainer: Make Training Data Vs. Vision Detector

ML Trainer: Make Training Data 对比 Vision Detector 的使用情况和统计数据

Creating original training data for Image Classification machine learning models just got a little easier! ML Trainer allows developers to quickly capture and export thousands of images to the Photos app, allowing every image to be imported with iCloud or the built in Image Capture app on Mac. Press the Scan button to capture a preset amount of images as you move closer to or pivot around your subject, or Tap the Camera button to capture a single picture. Toggle the Flashlight to improve results in low light conditions, and tap the Save button to export any captured images to the Photos app. While each image is always captured at a speed of 3 Frames Per Second, you can adjust the Frame Count of each Scan in the Settings Menu. A larger Frame Count will save you time, while a lower Frame Count will help improve accuracy across different angles. Enabling Crosshairs and Guides in the Settings Menu can also help improve accuracy. This app was specifically designed to speed up the process of importing data into the Xcode Developer Tool named CreateML. Exported images should also be compatible with other platforms like TensorFlow and Azure Machine Learning. A wired connection to a macOS device with the Image Capture app open will always be the fastest way to import your data to desktop.

Apple 应用商店
付费
开发者工具

商店排名

- -

Vision Detector

Vision Detector lets you run Core ML models directly on your iPhone or iPad without building an app in Xcode. It provides a simple way to test and evaluate machine learning models on real devices using on-device inference. To get started, create a machine learning model in Core ML format using Create ML or coremltools. Copy the model file to your device using the Files app. Supported locations include local storage and cloud services such as iCloud Drive, OneDrive, Google Drive, and Dropbox. Models can also be transferred using AirDrop. After launching Vision Detector, select and load your model. You can choose an input image from multiple sources: • Live video from the built-in camera with continuous inference • Still photos captured with the camera • Images from the Photo Library • Images from the file system For live video input, inference runs continuously on the camera feed. Performance such as frame rate depends on the device. Supported model types: • Image classification • Object detection • Style transfer Models that rely on MultiArray inputs or outputs, or that do not include a non-maximum suppression layer, are not supported. Note: Vision Detector does not include any pre-trained machine learning models. You must provide your own Core ML model to use the app.