AI Lab vs CoreMLCompare

AI Lab is a playful way to explore machine learning on your iPhone and iPad. Point your camera at anything and watch AI name what it sees — instantly and entirely on your device. New: hold it up to the world and let it listen, too. Two ways to sense the world • Camera: live, on-device image recognition with clear, ranked confidence and the top result featured front and centre • Microphone: recognise everyday sounds — no download, powered by Apple's built-in sound classifier A whole library of models Start right away with Apple's built-in Vision classifier (nothing to download), then add more advanced CoreML models when you want them — from fast and tiny to state of the art. Each model shows its release year, a power rating and its download size, so you always know what you're getting. Search and browse by category: objects, scenes, people, food and more. Made to explore • One-tap quick actions for live recognition and listening, right next to search • Compare two models on the same photo, side by side — take a new photo or pick one from your library • Share a comparison as a beautifully formatted email, with the photo and each model's results • Tap any result to learn more, and freeze a frame to save it to your photos • Manage storage: see sizes, track download progress, cancel or remove models Built for everyone • Hear the top result read aloud — ideal for VoiceOver users and hands-free use • Adjust speech in Settings: on/off, speed, language and voice, with a mute button on the recognition screen • Dynamic Type and clear, high-contrast labels throughout Privacy first Your photos and audio are processed entirely on your device and are never uploaded. AI Lab shows no ads and never sells your data; only anonymous, aggregate usage statistics help us make the app better. A note on accuracy The models are provided as-is. Recognition is a probability, not a fact — results can be wrong, and models that estimate sensitive traits (such as age, gender or emotion) are approximate and should never be treated as truth about a real person. A newer, more powerful device makes everything faster and more fun.

CoreMLCompare allows CoreML models to be easily compared and tested in real-time using the Vision Framework. The purpose is to seamlessly compare different models when detecting objects or quickly test your trained model, without the need to build your own test app. Features: - Import a new model either by using the pasteboard or after downloading the .mlmodel file on the device (browser download) - Change the model default name and configure a different color for it - Each model can be configured with a different minimum confidence level between 40% and 90% - Stopping specific models from detecting objects - using 4 models in parallel is quite processing-intensive - Can detect hot dogs (or bananas)