This model run coreml result is not right, the precision is completely wrong, I posted a PhotoDepthAnythingConv.onnx model: https://github.com/MoonCodeMaster/CoremlErrorModel/tree/main/DepthAnything
Core ML
RSS for tagIntegrate machine learning models into your app using Core ML.
Posts under Core ML tag
118 Posts
Sort by:
Post
Replies
Boosts
Views
Activity
Hello,
I have created a Neural Network → K Nearest Neighbors Classifier with python.
# followed by k-Nearest Neighbors for classification.
import coremltools
import coremltools.proto.FeatureTypes_pb2 as ft
from coremltools.models.nearest_neighbors import KNearestNeighborsClassifierBuilder
import copy
# Take the SqueezeNet feature extractor from the Turi Create model.
base_model = coremltools.models.MLModel("SqueezeNet.mlmodel")
base_spec = base_model._spec
layers = copy.deepcopy(base_spec.neuralNetworkClassifier.layers)
# Delete the softmax and innerProduct layers. The new last layer is
# a "flatten" layer that outputs a 1000-element vector.
del layers[-1]
del layers[-1]
preprocessing = base_spec.neuralNetworkClassifier.preprocessing
# The Turi Create model is a classifier, which is treated as a special
# model type in Core ML. But we need a general-purpose neural network.
del base_spec.neuralNetworkClassifier.layers[:]
base_spec.neuralNetwork.layers.extend(layers)
# Also copy over the image preprocessing options.
base_spec.neuralNetwork.preprocessing.extend(preprocessing)
# Remove other classifier stuff.
base_spec.description.ClearField("metadata")
base_spec.description.ClearField("predictedFeatureName")
base_spec.description.ClearField("predictedProbabilitiesName")
# Remove the old classifier outputs.
del base_spec.description.output[:]
# Add a new output for the feature vector.
output = base_spec.description.output.add()
output.name = "features"
output.type.multiArrayType.shape.append(1000)
output.type.multiArrayType.dataType = ft.ArrayFeatureType.FLOAT32
# Connect the last layer to this new output.
base_spec.neuralNetwork.layers[-1].output[0] = "features"
# Create the k-NN model.
knn_builder = KNearestNeighborsClassifierBuilder(input_name="features",
output_name="label",
number_of_dimensions=1000,
default_class_label="???",
number_of_neighbors=3,
weighting_scheme="inverse_distance",
index_type="linear")
knn_spec = knn_builder.spec
knn_spec.description.input[0].shortDescription = "Input vector"
knn_spec.description.output[0].shortDescription = "Predicted label"
knn_spec.description.output[1].shortDescription = "Probabilities for each possible label"
knn_builder.set_number_of_neighbors_with_bounds(3, allowed_range=(1, 10))
# Use the same name as in the neural network models, so that we
# can use the same code for evaluating both types of model.
knn_spec.description.predictedProbabilitiesName = "labelProbability"
knn_spec.description.output[1].name = knn_spec.description.predictedProbabilitiesName
# Put it all together into a pipeline.
pipeline_spec = coremltools.proto.Model_pb2.Model()
pipeline_spec.specificationVersion = coremltools._MINIMUM_UPDATABLE_SPEC_VERSION
pipeline_spec.isUpdatable = True
pipeline_spec.description.input.extend(base_spec.description.input[:])
pipeline_spec.description.output.extend(knn_spec.description.output[:])
pipeline_spec.description.predictedFeatureName = knn_spec.description.predictedFeatureName
pipeline_spec.description.predictedProbabilitiesName = knn_spec.description.predictedProbabilitiesName
# Add inputs for training.
pipeline_spec.description.trainingInput.extend([base_spec.description.input[0]])
pipeline_spec.description.trainingInput[0].shortDescription = "Example image"
pipeline_spec.description.trainingInput.extend([knn_spec.description.trainingInput[1]])
pipeline_spec.description.trainingInput[1].shortDescription = "True label"
pipeline_spec.pipelineClassifier.pipeline.models.add().CopyFrom(base_spec)
pipeline_spec.pipelineClassifier.pipeline.models.add().CopyFrom(knn_spec)
pipeline_spec.pipelineClassifier.pipeline.names.extend(["FeatureExtractor", "kNNClassifier"])
coremltools.utils.save_spec(pipeline_spec, "../Models/FaceDetection.mlmodel")
it is from the following tutorial: https://machinethink.net/blog/coreml-training-part3/
It Works and I were am to include it into my project:
I want to train the model via the MLUpdateTask:
ar batchInputs: [MLFeatureProvider] = []
let imageconstraint = (model.model.modelDescription.inputDescriptionsByName["image"]?.imageConstraint)
let imageOptions: [MLFeatureValue.ImageOption: Any] = [
.cropAndScale: VNImageCropAndScaleOption.scaleFill.rawValue]
var featureProviders = [MLFeatureProvider]()
//URLS where images are stored
let trainingData = ImageManager.getImagesAndLabel()
for data in trainingData{
let label = data.key
for imgURL in data.value{
let featureValue = try MLFeatureValue(imageAt: imgURL, constraint: imageconstraint!, options: imageOptions)
if let pixelBuffer = featureValue.imageBufferValue{
let featureProvider = FaceDetectionTrainingInput(image: pixelBuffer, label: label)
batchInputs.append(featureProvider)}}
let trainingData = MLArrayBatchProvider(array: batchInputs)
When calling the MLUpdateTask as follows, the context.model from completionHandler is null.
Unfortunately there is no other Information available from the compiler.
do{
debugPrint(context)
try context.model.write(to: ModelManager.targetURL)
}
catch{
debugPrint("Error saving the model \(error)")
}
})
updateTask.resume()
I get the following error when I want to access the context.model: Thread 5: EXC_BAD_ACCESS (code=1, address=0x0)
Can some1 more experienced tell me how to fix this?
It seems like I am missing some parameters?
I am currently not splitting the Data when training into train and test data. only preprocessing im doing is scaling the image down to 227x227 pixels.
Thanks!
Hey, i just created and trained an MLImageClassifier via the MLImageclassifier.train() method (https://developer.apple.com/documentation/createml/mlimageclassifier/train(trainingdata:parameters:sessionparameters:))
For my Trainingdata (MLImageclassifier.DataSource) i am using my directoy structure, so i got an images folder with subfolders of person1, person2, person3 etc. which contain images of the labeled persons (https://developer.apple.com/documentation/createml/mlimageclassifier/datasource/labeleddirectories(at:))
I am saving the checkpoints and sessions in my appdirectory, so i can create an MLIMageClassifier from an exisiting MLSession and/or MLCheckpoint.
My question is: is there any way to add new labels, optimally from my directoy strucutre, to an MLImageClassifier which i create from an existing MLCheckpoint/MLSession?
So like adding a person4 and training my pretrained Classifier with only that person4.
Or is it simply not possible and i have to train from the beginning everytime i want to add a new label?
Unfortunately i cannot find anything in the API.
Thanks!
Hey,
im training an MLImageClassifier via the train()-method:
guard let job = try? MLImageClassifier.train(trainingData: trainingData, parameters: modelParameter, sessionParameters: sessionParameters) else{
debugPrint("Training failed")
return
}
Unfortunately the metrics of my MLProgress, which is created from the returning MLJob while training are empty.
Code for listening on Progress:
job.progress.publisher(for: \.fractionCompleted)
.sink{[weak job] fractionCompleted in
guard let job = job else {
debugPrint("failure in creating job")
return
}
guard let progress = MLProgress(progress: job.progress) else {
debugPrint("failure in creating progress")
return
}
print("ProgressPROGRESS: \(progress)")
print("Progress: \(fractionCompleted)")
}
.store(in: &subscriptions)
Printing the Progress ends in:
MLProgress(elapsedTime: 2.2328420877456665, phase: CreateML.MLPhase.extractingFeatures, itemCount: 32, totalItemCount: Optional(39), metrics: [:])
Got the Same result when listening to MLCheckpoints, Metrics are empty aswell:
MLCheckpoint(url: URLPATH.checkpoint, phase: CreateML.MLPhase.extractingFeatures, iteration: 32, date: 2024-04-18 11:21:18 +0000, metrics: [:])
Can some1 tell me how I can access the metrics while training?
Thanks!
I hope this message finds you well. I recently had the opportunity to watch the insightful session titled "Improve Core ML Integration with Async Prediction" and was thoroughly impressed by the depth of information and the practical demonstration provided. The session offered valuable insights that I believe would greatly benefit my ongoing projects and my understanding of Core ML integration.
As I am keen on implementing the demonstrated workflows and techniques within my own work, I am reaching out to kindly request access to the source code and any related material presented during the session. Having access to the code would enable me to better understand the concepts discussed and apply them more effectively in real-world scenarios.
I believe that being able to review and experiment with the actual code would significantly enhance my learning experience and the implementation efficiency of my projects. It would also serve as a valuable resource for referencing best practices in Core ML integration and async prediction techniques.
Thank you very much for considering my request. I greatly appreciate the effort that went into creating such an informative session and am looking forward to potentially exploring the material in greater depth.
Best regards,
Fabio G.
The CoreML model worked correctly in the “Preview” of “CreateML”.
However, after it is put into the Xcode project and replaced the “MobileNetV2” , it did not classify the images correctly, it returned one image with high confidence all the time no matter what image it is .
The same code works fine when executed on real device.
Can someone please assist on this ?
Hello Developers,
We are trying to convert Pytorch models to CoreML using coremltools,
while converting we used jit.trace to create trace of model where we encountered a warning that if model has controlflow and conditions it is not advisable to use trace instead convert into TorchScript using jit.script,
However after successful conversion of model into TorchScript, Now in the next step of conversion from TorchScript to CoreML here is the error we are getting when we tried to convert to coremltools python package.
This root error is so abstract that we are not able to trace-back from where its occurring.
AssertionError: Item selection is supported only on python list/tuple objects
We trying to add this above error prompt into ChatGPT and we get something like the below response from ChatGPT. But unfortunately it's not working.
The error indicates that the Core ML converter encountered a TorchScript operation involving item selection (indexing or slicing) on an object that it doesn't recognize as a Python list or tuple. The converter supports item selection only on these Python container types. This could happen if your model uses indexing on tensors or other types not recognized as list or tuple by the Core ML tools. You may need to revise the TorchScript code to ensure it only performs item selection on supported types or adjust the way tensors are indexed.
I've been recently working on a VisionOS app which uses CoreMl to identify specific body parts and display a window with information of the identified body part, since the use of Vision Pro's cameras is blocked, I'm using an iPhone to perform image classification, and then send the label to the headset using Multipeer Connectivity, I'd like to display a volume once the user selects a body part, could my iPhone return enough spatial information for me to be able to fully take advantage of Vision Pro's mixed reality capabilities?
Hello I am making a rock paper scissors game using object detection with a model I made using create ml and a dataset I found online. The trained model works and I tried to implement it into Xcode but when I run my app I get this error
This neural network model does not have a parameter for requested key 'precisionRecallCurves'. Note: only updatable neural network models can provide parameter values and these values are only accessible in the context of an MLUpdateTask completion or progress handler.
I am still new to create ml and I cannot seem to find anything about making my model updatable in create ml.
I'm working with MLSoundClassifier to try to look for 2 different sounds in a live audio stream. I have been debating with the team if it is better to train 2 separate models, one for each different sound, or train 1 model on both sounds? Has anyone had any experience with this. Some of us believe that we have received better results with the separate models and some with 1 single model trained on both sounds. Thank you!
In investigating a capture session crash, it's unclear what's causing occasional system pressure interruptions, except that it's happening on older iOS devices. Does Low Power Mode have a meaningful impact on whether these interruptions happen?
How do I add a already made CoreML model into my playground? I tried what people recommended online -- building a test project and get the .mlmodelc file and put that in the playground along with the autogenerated class for the model. However, I keep on getting so many errors.
The errors:
Unexpected duplicate tasks
Target 'help' (project 'help') has write command with output /Users/cpulipaka/Library/Developer/Xcode/DerivedData/help-appuguzbduqvojfwkaxtnqkozecv/Build/Intermediates.noindex/Previews/help/Intermediates.noindex/help.build/Debug-iphonesimulator/help.build/adc7818afdf4ae03fd98cdd618954541.sb
Target 'help' (project 'help') has write command with output /Users/cpulipaka/Library/Developer/Xcode/DerivedData/help-appuguzbduqvojfwkaxtnqkozecv/Build/Intermediates.noindex/Previews/help/Intermediates.noindex/help.build/Debug-iphonesimulator/help.build/adc7818afdf4ae03fd98cdd618954541.sb
Unexpected duplicate tasks
Showing Recent Issues
Target 'help' (project 'help'): CoreMLModelCompile /Users/cpulipaka/Library/Developer/Xcode/DerivedData/help-appuguzbduqvojfwkaxtnqkozecv/Build/Intermediates.noindex/Previews/help/Products/Debug-iphonesimulator/help.app/ /Users/cpulipaka/Desktop/help.swiftpm/Resources/ZooClassifier.mlmodel
Target 'help' (project 'help'): CoreMLModelCompile /Users/cpulipaka/Library/Developer/Xcode/DerivedData/help-appuguzbduqvojfwkaxtnqkozecv/Build/Intermediates.noindex/Previews/help/Products/Debug-iphonesimulator/help.app/ /Users/cpulipaka/Desktop/help.swiftpm/Resources/ZooClassifier.mlmodel
ZooClassifier.mlmodel: No predominant language detected. Set COREML_CODEGEN_LANGUAGE to preferred language.
I am trying to coremltools.converters.convert a traced PyTorch model and I got an error:
PyTorch convert function for op 'intimplicit' not implemented
I am trying to convert a RVC model from github.
I traced the model with torch.jit.trace and it fails. So I traced down the problematic part to the ** layer : https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/infer/lib/infer_pack/modules.py#L188
import torch
import coremltools as ct
from infer.lib.infer_pack.modules import **
model = **(192, 5, dilation_rate=1, n_layers=16, ***_channels=256, p_dropout=0)
model.remove_weight_norm()
model.eval()
test_x = torch.rand(1, 192, 200)
test_x_mask = torch.rand(1, 1, 200)
test_g = torch.rand(1, 256, 1)
traced_model = torch.jit.trace(model,
(test_x, test_x_mask, test_g),
check_trace = True)
x = ct.TensorType(name='x', shape=test_x.shape)
x_mask = ct.TensorType(name='x_mask', shape=test_x_mask.shape)
g = ct.TensorType(name='g', shape=test_g.shape)
mlmodel = ct.converters.convert(traced_model,
inputs=[x, x_mask, g])
I got an error RuntimeError: PyTorch convert function for op 'intimplicit' not implemented.
How could I modify the **::forward so it does not generate an intimplicit operator ?
Thanks
David
I run a MiDaS CoreML model on the Device.
It run well on VisionPro Simulator and iOS RealDevice.
But crash on VisionPro device.
crash mssage:
/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShaders/MPSCore/Utility/MPSLibrary.mm:550: failed assertion `MPSKernel MTLComputePipelineStateCache unable to load function ndArrayConvolution2DA14.
Crashlog_com.moemiku.VisionMagicPhoto_2024-01-21-16-01-07.txt
Crashlog_com.moemiku.VisionMagicPhoto_2024-01-21-16-00-39.txt
Hi, I'm using apple/ml-stable-diffusion package with CoreML models running under GPU mode in my SwiftUI app. The problem that I have and every other implementation I have tested is that every time the model is changed the old model still persists I'm memory until the app is reset. This is the same for every app I have tested that uses this package. So my question is can I kill the sub processes or flush the memory. The package has memory freeing functions, but they don't affect the loaded model.
Any clues as to where I might start looking?
I have multiple ML models along with a collection of supporting code designed to enhance their effectiveness. I want to encapsulate these assets within a package so I can add it to a few of my projects. Is it possible to encrypt the ML models when including them as resources within the package?
Have a CoreML model that I run in my app Spatial Media Toolkit which lets you convert 2D photos to Spatial.
Running the model on my 13" M1 mac gets 70ms inference. Running the exact same code on my Vision Pro takes 700ms. I'm working on adding video support but Vision Pro inference is feeling impossible due to 700ms per frame (20x realtime for for 30fps! 1 sec of video takes 20 sec!)
There's a ModelConfiguration you can provide, and when I force CPU I get the same exact performance.
Either it's only running on CPU, the NeuralEngine is throttled, or maybe GPU isn't allowed to help out. Disappointing but also feels like a software issue. Would be curious if anyone else has hit this/have any workarounds
Is 30x30 the maximum grid size on Create ML App?
The input allows me to set any number higher than that, but on starting training, the number falls back to 30x30.
Is that a limitation or a bug in the app?
Trying to learn vision apps and I was wondering if the actual .xcodeproj file was available anywhere. I understand there are snippets of code below the video but it's difficult to learn how to build an app with those files since it just focuses on the ML aspect.
https://developer.apple.com/videos/play/wwdc2021/10039/
I'm also looking for the code for this video specifically. I'm aware of the drawing code but that is a relatively simple example to understand and the CreateML stuff isn't prevalent in that.
I have been attempting to debug this for over 10 hours...
I am working on implementing Apple's MobileNetV2 CoreML model into a Swift Playgrounds. I performed the following steps
Compiled CoreML model in regular Xcode project
Moved Compiled CoreML (MobileNetV2.mlmodelc) model to Resources folder of Swift Playground
Copy Paste the model class (MobileNetV2.swift) into the Sources folder of Swift Playground
Use UIImage extensions to resize and convert UIImage into CVbuffer
Implement basic code to run the model.
However, every time I run this, it keeps giving me this error:
MobileNetV2.swift:100: Fatal error: Unexpectedly found nil while unwrapping an Optional value
From the automatically generated model class function:
/// URL of model assuming it was installed in the same bundle as this class
class var urlOfModelInThisBundle : URL {
let bundle = Bundle(for: self)
return bundle.url(forResource: "MobileNetV2", withExtension:"mlmodelc")!
}
The model builds perfectly, this is my contentView Code:
import SwiftUI
struct ContentView: View {
func test() -> String{
// 1. Load the image from the 'Resources' folder.
let newImage = UIImage(named: "img")
// 2. Resize the image to the required input dimension of the Core ML model
// Method from UIImage+Extension.swift
let newSize = CGSize(width: 224, height: 224)
guard let resizedImage = newImage?.resizeImageTo(size: newSize) else {
fatalError("⚠️ The image could not be found or resized.")
}
// 3. Convert the resized image to CVPixelBuffer as it is the required input
// type of the Core ML model. Method from UIImage+Extension.swift
guard let convertedImage = resizedImage.convertToBuffer() else {
fatalError("⚠️ The image could not be converted to CVPixelBugger")
}
// 1. Create the ML model instance from the model class in the 'Sources' folder
let mlModel = MobileNetV2()
// 2. Get the prediction output
guard let prediction = try? mlModel.prediction(image: convertedImage) else {
fatalError("⚠️ The model could not return a prediction")
}
// 3. Checking the results of the prediction
let mostLikelyImageCategory = prediction.classLabel
let probabilityOfEachCategory = prediction.classLabelProbs
var highestProbability: Double {
let probabilty = probabilityOfEachCategory[mostLikelyImageCategory] ?? 0.0
let roundedProbability = (probabilty * 100).rounded(.toNearestOrEven)
return roundedProbability
}
return("\(mostLikelyImageCategory): \(highestProbability)%")
}
var body: some View {
VStack {
let _ = print(test())
Image(systemName: "globe")
.imageScale(.large)
.foregroundColor(.accentColor)
Text("Hello, world!")
Image(uiImage: UIImage(named: "img")!)
}
}
}
Upon printing my bundle contents, I get these:
["_CodeSignature", "metadata.json", "__PlaceholderAppIcon76x76@2x~ipad.png", "Info.plist", "__PlaceholderAppIcon60x60@2x.png", "coremldata.bin", "{App Name}", "PkgInfo", "Assets.car", "embedded.mobileprovision"]
Anything would help 🙏
For additional reference, here are my UIImage extensions in ExtImage.swift:
//Huge thanks to @mprecke on github for these UIImage extension function.
import Foundation
import UIKit
extension UIImage {
func resizeImageTo(size: CGSize) -> UIImage? {
UIGraphicsBeginImageContextWithOptions(size, false, 0.0)
self.draw(in: CGRect(origin: CGPoint.zero, size: size))
let resizedImage = UIGraphicsGetImageFromCurrentImageContext()!
UIGraphicsEndImageContext()
return resizedImage
}
func convertToBuffer() -> CVPixelBuffer? {
let attributes = [
kCVPixelBufferCGImageCompatibilityKey: kCFBooleanTrue,
kCVPixelBufferCGBitmapContextCompatibilityKey: kCFBooleanTrue
] as CFDictionary
var pixelBuffer: CVPixelBuffer?
let status = CVPixelBufferCreate(
kCFAllocatorDefault, Int(self.size.width),
Int(self.size.height),
kCVPixelFormatType_32ARGB,
attributes,
&pixelBuffer)
guard (status == kCVReturnSuccess) else {
return nil
}
CVPixelBufferLockBaseAddress(pixelBuffer!, CVPixelBufferLockFlags(rawValue: 0))
let pixelData = CVPixelBufferGetBaseAddress(pixelBuffer!)
let rgbColorSpace = CGColorSpaceCreateDeviceRGB()
let context = CGContext(
data: pixelData,
width: Int(self.size.width),
height: Int(self.size.height),
bitsPerComponent: 8,
bytesPerRow: CVPixelBufferGetBytesPerRow(pixelBuffer!),
space: rgbColorSpace,
bitmapInfo: CGImageAlphaInfo.noneSkipFirst.rawValue)
context?.translateBy(x: 0, y: self.size.height)
context?.scaleBy(x: 1.0, y: -1.0)
UIGraphicsPushContext(context!)
self.draw(in: CGRect(x: 0, y: 0, width: self.size.width, height: self.size.height))
UIGraphicsPopContext()
CVPixelBufferUnlockBaseAddress(pixelBuffer!, CVPixelBufferLockFlags(rawValue: 0))
return pixelBuffer
}
}