Profile Photo
I am using mlmodel created from keras model that used (64,64,3) numpy array. Xcode asks for MLMultiArray with dimensions (3,64,64), However I failed to find examples of creating MLMultiArray. I would greatly appriciate if you could describe how it can be done or gave an example.
in Machine Learning
Profile Photo
I've converted pix2pix model whose input/output is Image(256x256)   But the model are normalized to the range [-1,1], and the output image shows nothing but black.   Does anyone know how to convert this image to [0, 255]?
in Machine Learning
Profile Photo
I have tried various ways to convert my Keras model to core ml using core ml tools, but it gives me this error. Keras layer '<class 'tensorflow.python.keras.engine.input_layer.InputLayer'>' not supported.     This is how my model looks. img_input = layers.Input(shape=(224, 224, 3))   seed = 230 numpy.random.seed(seed)     x =… (Show more)
in Machine Learning
Profile Photo
I created a simple ImageClassifier.mlmodel with MLImageClassifierBuilder (import CreateMLUI). My question is: Is there a way to know how many layers have my model and which kind of layers they are (conv,pool,etc.)?   Thanks in advance, Alice
in Machine Learning
Profile Photo
My trained model is working fine on Xcode (11 Beta) on my computer but when deployed to my iphone to try it out, it is not predicting anything. Anyone encountered this problem and has an idea why or has a solution? Thank-you!
in Machine Learning
Profile Photo
Hi, All.   Can I make dcGAN using CoreML or CreateML?   I want to run dcGAN in my mac with GPU.   Thanks.   Best @bemoregt.
in Machine Learning
Profile Photo
Hey everyone,   Just wondering if anyone knows how to create a coreML model with the "update" parameter. It doesn't let you do it in createML and Apple only has information on how to use the parameter once it's already there, but not how to mark the model as updatable.   Thanks, Jordan.
in Machine Learning