hypermodel | : space_invader : related model builder library | Animation library

Your code should look like:

Unfortunately doing a validation_split=0.2 does not work in this case, because this argument assumes that the data is a Tensor or a NumPy array. Since you have the data stored as a generator (which is a good idea), you can't simply split it.

You'll need to create a validation generator, just like you did with test_data_gen, and change validation_split=0.2 to validation_data=val_data_gen.

One way to convert an image dataset into X and Y NumPy arrays are as follows:

NOTE: This code is borrowed from here. This code is written by "PARASTOOP" on Github.

You need to create the Train and Test split like this:

Kernel size should be 3x3 not 3 . i.e kernel_size=(3,3) . Kernel is a matrix and not a single digit.

RuntimeError: Model-building function did not return a valid Keras Model instance, found (, )

(, )

As you can see this a tuple of two Keras Model instance. This is output of create_autoencoder(hp, input_dim, output_dim).

You have to change the parameters inside the T2V layer and inside your network in order to correctly match the shapes

Having worked with autokeras recently, I can share my little knowledge.

1. Task API When doing a classical task such as image classification/regression, text classification/regression, ..., you can use the simplest APIs provided by autokeras called Task API: ImageClassifier, ImageRegressor, TextClassifier, TextRegressor, ... In this case you have one input (image or text or tabular data, ...) and one output (classification, regression).

2. Automodel However when you are in a situation where you have for example a task that requires multi inputs/outputs architecture, then you cannot use directly Task API, and this is where Automodel comes into play with the I/O API. you can check the example provided in the documentation where you have two inputs (image and structured data) and two outputs (classification and regression)

3. GraphAutoModel GraphAutomodel works like keras functional API. It assembles different blocks (Convolutions, LSTM, GRU, ...) and create a model using this block, then it will look for the best hyperparameters given this architecture you provided. Suppose for instance I want to do a binary classification task using time series as input data. First let's generate a toy dataset :

Looks like you hit a bug in HyperModel with the full_messages method. AFAIK all the other methods would work fine in your example.

If you look at https://github.com/hyperstack-org/hyperstack/issues/143 there is a work around patch to apply if you really need full_messages