Stack Overflow
Stack Overflow

Questions tagged [auto-keras]

Auto-Keras is an open source software library for automated machine learning (AutoML), written in Python. A question tagged auto-keras shoud be related to the Auto-Keras Python package.

Auto-Keras is an open source software library for automated machine learning (AutoML). It is developed by DATA Lab at Texas A&M University and community contributors. The ultimate goal of AutoML is to provide easily accessible deep learning tools to domain experts with limited data science or machine learning background. Auto-Keras provides functions to automatically search for architecture and hyperparameters of deep learning models.

58 questions
1
vote
3 answers

ModuleNotFoundError: No module named 'autokeras.image_supervised'

Installed AutoKeras and pre-reqs in 3.6 Python environment using Anaconda. Trying to test AutoKeras in Jupyter, but keep getting this error: ModuleNotFoundError: No module named 'autokeras.image_supervised'
Anthony Richardson
  • 19
  • 1
  • 6
0
votes
0 answers

How to model a shared layer in AutoKeras?

I want to share a layer between for two inputs: x --> F(x) ==> G(F(x),F(y)) y --> F(y) In Keras, it can be done by defining a layer then passing two inputs separately to the layer, is it possible to do it in AutoKeras?
Panda
  • 231
  • 3
  • 17
0
votes
0 answers

Why is AutoKeras max_model_size not working?

I am trying to constrain the max params used by AutoKeras ImageClassifier to 1mil using max_model_size = 1000000. However, when I do this I immediately get the error: "FailedTrialError: Oversized model: 23538689 parameters. Skip model." When I don't…
TheyTakingTheHobbitsToIsengard
  • 71
  • 11
0
votes
0 answers

Autokeras - StructuredDataClassifier, Graph execution error:

I used this callback in autokeras: from tensorflow.keras.callbacks import EarlyStopping early_stopping = EarlyStopping(monitor='val_loss', patience=5) auto_ml.fit(x=x_train, y=y_train, validation_data=(x_test, y_test), class_weight=class_weights,…
imnotnationalPark
  • 1
0
votes
1 answer

Tensorflow and AutoKeras loaded models - ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float)

I'm looking for a solution to my issue, and I tried several suggestions with no success. I hope someone can help me with this. I used Autokeras to train and save a model. I used the following code to save the best model. try: …
lvfmc85
  • 1
  • 1
0
votes
1 answer

NumPy array value error from training in Auto-Keras with StratifiedKFold

Background My sentiment analysis research comes across a variety of datasets. Recently I've encountered one dataset that somehow I just cannot train successfully. I mostly work with open data in .CSV file format, hence Pandas and NumPy are heavily…
CMYang
  • 166
  • 8
0
votes
0 answers

Different results between training and loading autokeras-model

I trained a regression-model with autokeras resulting in a model with a MAE of 0.2 with that code, where x and y were input and output-dataframes: X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=1) search =…
Flo
  • 11
  • 1
0
votes
1 answer

Can not load saved model in keras / tensorflow?

I trained the model using autokeras with TensorFlow 2.5. I saved the pre-trained model using both methods explained on Keras (TensorFlow) home page. model.save(f'model_auto_keras{max_trials}.h5') model.save("keras_test_save_model") again when I want…
krishna
  • 1
  • 3
0
votes
0 answers

To fit images file to an autokeras image classifier

I am trying to fit images file to an autokeras image classifier. Code I am using is given below, import autokeras as ak import os import numpy as np from sklearn.model_selection import train_test_split path=…
swetha sreedhar
  • 1
  • 3
0
votes
2 answers

module 'keras.layers.normalization' has no attribute 'BatchNormalizationBase'

when i run this code import os from autokeras import StructuredDataClassifier import stellargraph as sg from stellargraph.mapper import FullBatchNodeGenerator from tensorflow.keras import layers, optimizers, losses, metrics, Model from…
muhammad
  • 37
  • 2
  • 7
0
votes
0 answers

Get trial number in Keras callback function using Autokeras

I'm running an autokeras training, and I want to compute the global progress of the training, where the progress is defined by the total epochs run, including previous trials. Unfortunatelly, I don't know how to get the trial number, or how to keep…
Israel Varea
  • 2,600
  • 2
  • 17
  • 24
0
votes
0 answers

Autokeras - Get classes name

I am trying to get the classes names I used for Autokeras. Both sentences and labels are strings. import pandas as pd import autokeras as ak df = pd.read_csv("train.csv", names=['text', 'category']) sentences = df.text.values labels =…
Juanvulcano
  • 1,354
  • 3
  • 26
  • 44
0
votes
2 answers

Issue replicating AutoKeras StructuredDataClassifier

I have a model that I generated using AutoKeras and I want to replicate the model so that I can construct it with keras tuner to do further hyperparameter tuning. But I am running into issues replicating the model. The model summary of the autokeras…
AlwaysNull
  • 348
  • 2
  • 4
  • 15
0
votes
2 answers

TypeError: Unsupported type for StructuredDataAdapter

can anyone help me to resolve above error? ### using trasnformers from sklearn.compose import ColumnTransformer from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer from sklearn.preprocessing import OneHotEncoder from…
Juned Ansari
  • 5,035
  • 7
  • 56
  • 89
0
votes
0 answers

AutoKeras: Exported then reloaded Classifier model does not predict correctly

UPDATE: As kindly pointed out by @Dr Snoopy in the comments below, I was mistaken in thinking that the matrix from the predict() would show the predicted labels - instead it shows classification probabilities. Issue: I am trying out AutoKeras by…
NoviceProg
  • 815
  • 1
  • 10
  • 22
1 2
3
4