Neural Object Detector vs Vision Detector

Neural Object Detector was designed to be used by both developers and people who are enthusiastic about Machine Learning, Computer Vision, and Object Detection / Image Classification using the combination of both. Neural Object Detector, by default is bundled with YOLOv3 model, which is a neural network for fast object detection that detects 80 different classes of objects. In addition to that, the app allows the users to import any custom machine learning model designed for object detection or image classification, with a single tap, the downloaded model can be imported via the Files app import window which is available within the app by simply pressing the plus icon on the models view so users do not have to leave the app. The app, based on the model selected, draws a rounded rectangle over the detected objects, the annotated image can be rendered and saved to photos or shared if the user chooses to share it directly from the app. To meet every users needs a handful of settings for computer vision algorithm and camera resolution can be changed. Users have the option to enable CPU only mode, which helps test their models under that specific condition. In addition to Object Detection, Neural also supports Image Classification, by default, Neural is bundled with Resnet50 Image Classification Model. Core ML* models which are a type of "Pipeline" in the format of *.mlmodel is supported by this app for Object Detection. No other model format is supported as of now. Core ML Supported Tools, Services, and Converters: • Turi Create* - https://github.com/apple/turicreate • IBM Watson Services* - https://developer.apple.com/ibm/ • Core ML Tools* - https://pypi.org/project/coremltools/ • Apache MXNet* - https://github.com/apache/incubator-mxnet/tree/master/tools/coreml • TensorFlow* - https://github.com/tf-coreml/tf-coreml • ONNX* - https://github.com/onnx/onnx-coreml * Turi Create, IBM Watson Services, Core ML, Apache MXNet, TensorFlow, ONNX might be registered trademarks of their respected owners / proprietors. Neural Object Detector nor the developer is not affiliated with any of the above services or companies. YOLOv3 Model bundled with the is app is free, open source model. More info: https://github.com/pjreddie/darknet Resnet50 Model bundled with this app for Image Classification is free, and open source model. More info: https://github.com/fchollet/deep-learning-models/blob/master/LICENSE Visit https://hariharanm.com/neural/acknowledgements/ for Acknowledgments. The machine learning aspects are all proceed on device so nothing leaves the device. No cloud services are involved. No private analytics services. If, a user decides to contact app support a handful of data will be complied into a log file and attached to the mail composer, these data include app version, app configuration, device model, battery info, device software version, CPU utilised my the app. If the user decided not share, they can simply delete it and continue with the composing the support mail. No data is that is individually identifiable is collected. https://hariharanm.com/

Vision Detector is an AI image analysis tool that supports CoreML machine learning models, multi-modal Large Language Models, and on-device Apple Intelligence. Choose the mode that best fits your use case. You can choose one of the following image input sources: - Live video by built-in camera - Still image by the built-in camera - Photo Library - Files (iCloud, Google Drive, Dropbox, etc) For live video inputs, continuous inference is performed on the camera feed. However, the frame rate and other parameters depend on the device. # Notification Center Vision Detector can call Notification Center for predefined conditions. Broadcasting notifications send notification to your all Apple devices signed in with the same Apple Account. ## CoreML Mode Vision Detector locally executes CoreML models using Apple’s Vision framework. Before using this mode, prepare a machine learning model in the CoreML format (.mlmodel or .mlpackage) using Create ML. Import ML models via iClpoud or AirDrop. Vision Detector supports the following types of CoreML models: - Image classification - Object detection - Style transfer ## Vision LLM Mode Vision Detector can use multi-modal large language model (LLMs). Define what to do with prompt as following samples: - If the image is screen shot, answer the name software - Call notification when you see a cat - Count number of persons in the image, and notify when it changes ## Apple Intelligence mode Available with iOS 27 on selected devices (iPhone 17 Pro, iPhone Air, etc). The images are completely processed on your device locally with your prompt.