Where communities thrive

  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
  • Jan 23 10:54
    adamivora starred keras-team/autokeras
  • Jan 23 02:17
    haifeng-jin synchronize #922
  • Jan 23 02:17

    haifeng-jin on preprocessing_layer

    fixing tests (compare)

  • Jan 22 21:25
    haifeng-jin synchronize #922
  • Jan 22 21:25

    haifeng-jin on preprocessing_layer

    update (compare)

  • Jan 22 19:19
    haifeng-jin commented #923
  • Jan 22 19:19
    haifeng-jin labeled #923
  • Jan 22 19:19
    haifeng-jin labeled #923
  • Jan 22 19:19
    haifeng-jin labeled #923
  • Jan 22 19:18
    haifeng-jin commented #878
  • Jan 22 17:17
  • Jan 22 16:56
    haifeng-jin commented #920
  • Jan 22 16:36
    haifeng-jin commented #921
  • Jan 22 15:41
    klgraham starred keras-team/autokeras
  • Jan 22 15:13
    mulka edited #923
  • Jan 22 15:12
    mulka opened #923
  • Jan 22 14:29
    mulka commented #878
  • Jan 22 08:47
    yuyang-huang starred keras-team/autokeras
  • Jan 22 07:46
    iXanthos commented #920
  • Jan 22 06:28
    KUASWoodyLIN starred keras-team/autokeras
Juan Park
Hello everyone, like @HYDesmondLiu, I am also looking at if there is an implementation for flow_from_directory or flow_from_dataframe.
Juan Park

Also, does anyone happen to have a code example of training a multilabel model?
I am feeding the ImageClassifier, trainX (of shape: (n_images, 199, 199, 3)) and trainY (of shape: (n_images, n_classes)).

    model = ak.ImageClassifier(verbose=True)
    model.fit(trainX, trainY, time_limit=seconds)

I am getting the error:

ValueError: Found input variables with inconsistent numbers of samples: [16933, 474124]

Where 474124 is n_classes*n_images. To me, it looks ImageClassifier assumes the labels to be in multiclass format (ie. class=[0, 1, 2, 3, 4....]).

Sinan Sivri
Hello everyone best practice is using autokeras with docker? i'm unable to install via pip
could you help?
Hi - I was wondering if anyone had any advice on how to use autokeras with multiple inputs?
for context, I am working on a vector classification problem (i.e. my output is a vector of non-softmax binary classifiers)
and I have a text input and an audio input
I'd like to keep them separate as the text input is non-embedded tokens (and would need to be embedded first somehow), so I don't think I can just concatenate them
concatenate text and audio input, I mean
@jhfjhfj1 is this channel monitored?
Huaiyi Zhao
Hi all.
Hi everyone. I am wondering how to use the funcion ''visualize’’ to see what a model looks like since i do not know where exactly can i get this function, more specificly, what part do i need to import?

Hi All,
Please you help me.
I try to use Supervised Class. it occur error TypeError as picture.
How to use Supervised Class.


Vijay Daita
I was wondering if you could use AutoKeras as a replacement for AutoML
How would it compare to something like fast.ai?
I can't find the example of cifar10 (keras-team/autokeras@85d972a), where is it?
anyone here?
How many epochs does it run on each model? And does Current Metric = train or test accuracy?
can someone help me integrate autokeras in my app?
Hi All,
Does anybody have any experience using AutoKeras with time series data?
I also would like to get some tips on which cuda / tensorflow / autokeras versions work best, trying to setup a docker env so I can share it with the people on my team
Fan Yang
Hi everybody,
I got this error"RuntimeError: Given groups=1, weight of size [2048, 6144, 1], expected input[128, 8192, 128] to have 6144 channels, but got 8192 channels instead
how to solve this?
Elad Rapaport
can autokeras be used for "image" data with more than 3 channels? I get "RuntimeError: running_mean should contain 3 elements not 22" when trying to run such a dataset but I was hoping that there is a tweak that can allow this?
Sravya Tirukkovalur
Hi all, I am looking into the code base of autokeras and reading through the paper, seems like APIs have changed quite a bit recently( may be after 0.4.0 release). For example: no more search.py, bayesian.py . Curious, when is the next release planned? Asking to understand if it might be better to wait to dig through the code for the next release.
Tomasz Latkowski
Hi all, i have a general question:
Does anyone try to train auto-keras on large datasets i.e. ImageNet?
I'm wondering how the results look like in comparison to RL-based NAS approaches
hello?can autokeras be used for "image" data with more than 3 channels?
Hey Guys, i try to train and predict with an Auto Model and a simple structrured Data Set ... 1 row input -1 row output ... almost linear. But ak.fit crashes after a few seconds
Hey, i am new to autokeras and i am trying to do the example of the task api. I get the error ValueError: Either validation_data or validation_splitshould be provided. if i put the code into juypter notebook. version is right anyone can help me?
Hi, anyone working with autokeras 1.0 on the Windows subsystem for linux? I am having trouble with CPU frequency management. In all examples I get 'NotImplementedError: can't find current frequency file' from psutil. Any ideas?
There is a "greedy" cifar10 tutorial that wants to import from "nas.greedy" but there is no such module, none that I can find anyway.
There is a "greedy" cifar10 tutorial that wants to import from "nas.greedy" but there is no such module, none that I can find anyway. https://github.com/datamllab/autokeras-algorithm/blob/master/examples/cifar10_tutorial.py -- Does the autokeras group perhaps have the module hiding someplace? Please let me know.
hi all , I got a Error when used autokeras
Traceback (most recent call last):
File "aktest.py", line 11, in <module>
clf.fit(x_train, y_train,validation_split=0.1)
File "/usr/local/lib/python3.6/dist-packages/autokeras/auto_model.py", line 123, in fit
preprocess_graph, keras_graph = self.hyper_graph.build_graphs(hp)
File "/usr/local/lib/python3.6/dist-packages/autokeras/hypermodel/graph.py", line 434, in build_graphs
plain_graph = self.hyper_build(hp)
File "/usr/local/lib/python3.6/dist-packages/autokeras/hypermodel/graph.py", line 454, in hyper_build
outputs = old_block.build(hp, inputs=inputs)
TypeError: _build_wrapper() got an unexpected keyword argument 'inputs'
how to solve this?
Alex Lau
@sparklelj Same here
Alex Lau
@sparklelj I found that the keras-tuner didn't pass the kwargs, so I have made a pull request for this: keras-team/keras-tuner#157
hello, everyone'
does auto keras provide support for LSTM (input shape (3000,7,10), output shape (3000,10), for exemple)
Leon Spors
How do you load own datasets with ak 1.0?
Andreas Backhaus
Hello everyone. Is there a possibility to get the keras model itself which was generated for example within the ImageClassifier? I would like to a) show its structure and b) save it for serving.
Hi everyone. How to solve "'Graph' object has no attribute 'produce_keras_model'" problem?
I use from autokeras.image.image_supervised import load_image_dataset, ImageClassifier
and clf.export_keras_model(MODEL_DIR)

Hands-On Machine Learning with Auto-Keras

Develop state-of-the-art machine learning models with just a few lines of code!

Get your copy for just $5. https://bit.ly/2sFRIph

hi there has anyone worked with autokeras image classifer