coreml

问题 I'm trying to integrate CoreML model into my app. The output is given by a MLMultiArray , but I want the data in it in order to generate an OpenCV matrix. There is a dataPointer property in MLMultiArray , which is a UnsafeMutableRawPointer . How can I pass it as a C's pointer so that I can directly use it to generate an OpenCV matrix? Thanks in advance! 回答1: I found a solution. I don't need to pass the dataPointer as C's pointer from Swift to Objective-C++. I can just pass the whole

问题 I am trying to load a .mlmodel file using the following code: let paths = FileManager.default.urls(for: .documentDirectory, in: .userDomainMask) var documentsUrl = paths[0] documentsUrl.appendPathComponent("parallel.mlmodel") do { let compiledModelUrl = try MLModel.compileModel(at: documentsUrl) let model = try? MLModel(contentsOf: compiledModelUrl) } catch { print(error.localizedDescription) } But I get the error The file couldn’t be saved. , the model does exist at that location. 回答1: I

问题 I'm using Keras 2.1.3 and I want to convert MobileNet to CoreML: from keras.applications import MobileNet from keras.applications.mobilenet import relu6 from keras.applications.mobilenet import DepthwiseConv2D import coremltools.converters.keras as k def save_model(): model = MobileNet(input_shape=(128,128,3), include_top=False) model.save('temp.h5') def convert(): model = k.convert('temp.h5', input_names=['input'], output_names=['output'], model_precision='float16', custom_conversion

问题 I have already converted the .mlmodel to .mlmodelc , and I have put it in the resources folder. Im using Vision framework and MNIST model, following this tutorial (https://www.youtube.com/watch?v=bOg8AZSFvOc), but using swift playground. What am i missing? (im using .playground files, not .playgroundbook files) line of code: guard let visionModel = try? VNCoreMLModel(for: MNIST().modelc) else {fatalError("can not load Vision ML model")} Error message: use of undefined identifier 'MNIST'

问题 I've got an array of 40 arrays with 12 double features, so the type is [[double]]. Currently I'm sending this data to Google Cloud ML API to get a related prediction. Since Apple recently introduced CoreML and coremltools, I converted my model from keras to .mlmodel to avoid thousand of google cloud api calls and do inference directly on my iPhone: coreml_model = coremltools.converters.keras.convert(new_Model, input_names=['accelerations'], output_names=['scores']) coreml_model.save(

问题 I am trying to start small and have trained my model with 2 items. It recognises both just fine but when I show it something other than the 2 items it knows, it keeps telling me that is is always the same item. For example, I have an apple and banana. If I show it the apple, it correctly gives me apple, if I show it a banana it correctly returns banana. But if I show it a dog, it tells me it is an apple. If I show it a helicopter it tells me it is an apple. I even tried an if statement to say

问题 I'm running an mlmodel that is coming from keras on an iPhone 6. The predictions often fails with the error Error computing NN outputs . Does anyone know what could be the cause and if there is anything I can do about it? do { return try model.prediction(input1: input) } catch let err { fatalError(err.localizedDescription) // Error computing NN outputs error } EDIT: I tried apple's sample project and that one works in the background so it seems it's specific to either our project or model

问题 I am having issues with Apple Turi Create and image classifier. I have successfully created a model with 22 categories. I have recently added 5 more categories and console is giving me error warning Please use dropna() to drop rows with missing target values. The full console log looks like this: [16:30:30] src/nnvm/legacy_json_util.cc:190: Loading symbol saved by previous version v0.8.0. Attempting to upgrade... [16:30:30] src/nnvm/legacy_json_util.cc:198: Symbol successfully upgraded!

问题 I am trying to retain the objects from the console to be shown in as a label(classifierText). The warning of "UILabel.text must be used from main thread only" appears. What seems to the problem as to why the items are being shown as the label? var previewLayer: AVCaptureVideoPreviewLayer! let classifierText: UILabel = { let classifier = UILabel() classifier.translatesAutoresizingMaskIntoConstraints = false classifier.textColor = .black classifier.font = UIFont(name: "Times-New-Roman", size:

问题 I am trying normalize the input of my CoreML model like below, it kind of does something to the array but its quite different then what SKLearn does(I give same input and watch output in these environments). So appereantly I do something wrong. My Model is trained with Keras and SKlearn and it must do the same normalization as I did using SKLearn Normalizer, which is the default L2 normalizer . What I am doing below apperantly is not equalivant of sklearn, any ideas? vDSP_normalizeD(vec, 1,