coreml

I'm testing Apple's Vision Alignment API and have questions regarding VNHomographicImageRegistrationRequest. Has anyone got it to work? I can get the warpTransform out of it, but I've yet to see a matrix that makes sense, meaning, I'm unable to get a result that warps the image back onto the source image. I'm using Opencv warpPerspective to handle the warping. I'm calling this to get the transform: class func homography(_ cgImage0 : CGImage!, _ cgImage1 : CGImage!, _ orientation : CGImagePropertyOrientation, completion:(matrix_float3x3?)-> ()) { let registrationSequenceReqHandler =

In Python, I trained an image classification model with keras to receive input as a [224, 224, 3] array and output a prediction (1 or 0). When I load the save the model and load it into xcode, it states that the input has to be in MLMultiArray format. Is there a way for me to convert a UIImage into MLMultiArray format? Or is there a way for me change my keras model to accept CVPixelBuffer type objects as an input. Matthijs Hollemans In your Core ML conversion script you can supply the parameter image_input_names='data' where data is the name of your input. Now Core ML will treat this input as

I am looking at Core ML Apple iOS framework. I have read that to install coremltools to create own models. I have installed python sudo python /Users/administrator/Downloads/get-pip.py As per document coreml installation I have downloaded coremltool file. and then trying to install coremltools https://pypi.python.org/pypi/coremltools When I installed coremltools on my mac, i got the following error. Please suggest me to solve this error. so that i can work on coremltools MyMacbook:~ administrator$ pip install -U /Users/administrator/Downloads/coremltools-0.3.0-py2.7-none-any.whl Processing .

In looking over the new CoreML API, I don't see any way to continue training the model after generating the .mlmodel and bundling it in your app. This makes me think that I won't be able to perform machine learning on my user's content or actions because the model must be entirely trained beforehand. Is there any way to add training data to my trained model after shipping? EDIT: I just noticed you could initialize a generated model class from a URL, so perhaps I can post new training data to my server, re-generate the trained model and download it into the app? Seems like it would work, but

I am using a .playground file and I can't seem to add my CoreML model to it. I drag it into the Resources folder and this is my code: func predict(image: CGImage) { let model = try! VNCoreMLModel(for: Inceptionv3().model) let request = VNCoreMLRequest(model: model, completionHandler: results) let handler = VNSequenceRequestHandler() try! handler.perform([request], on: image) } However, I get the error saying: Use of Undeclared Type Inceptionv3 Can someone please help me out? The compiler raises this error, because it cannot find a declaration of the class Inceptionv3, that you try to

Apple introduced Core ML. There are many third parties providing trained models. But what if I want to create a model myself? How can I do that and what tools & technologies can I use? Core ML doesn't provide a way to train your own models. You only can convert existing ones to Apple 'mlmodel' format. To create your own neural networks, use Caffe or Keras frameworks and then convert those models to CoreML format. For traditional machine learning algorithms Core ML is also compatible with Scikit-learn * and XGBoost . You can also train and run neural networks on iOS without Core ML, just use

While I have been researching best practices and experimenting multiple options for an ongoing project(i.e. Unity3D iOS project in Vuforia with native integration, extracting frames with AVFoundation then passing the image through cloud-based image recognition), I have come to the conclusion that I would like to use ARkit, Vision Framework, and CoreML; let me explain. I am wondering how I would be able to capture ARFrames, use the Vision Framework to detect and track a given object using a CoreML model. Additionally, it would be nice to have a bounding box once the object is recognized with