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
5
votes
0 answers

Why "I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version" can't finish

This is my data. it has 7 images: I using autokeras to training: import tensorflow as tf import numpy as np import autokeras as ak from tensorflow.keras.preprocessing import image BATCH_SIZE = 32 IMG_HEIGHT = 224 IMG_WIDTH = 224 train_data_dir =…
D T
  • 3,522
  • 7
  • 45
  • 89
5
votes
1 answer

semaphore_tracker: There appear to be 1 leaked semaphores to clean up at shutdown len(cache))

I was run an autokeras code via python3.6. There is a warning like this after trained one model: Saving model. …
Jonathan.H
  • 183
  • 1
  • 2
  • 10
4
votes
2 answers

Autokeras installation with Anaconda

I have problems with installing Autokeras with Anaconda. I downgraded python to 3.6 I installed pytorch and downgraded to version 0.4.1 I downgraded numpy to 1.14.5 I installed visual studio C++ build tool But now I get the error that…
Florida Man
  • 2,021
  • 3
  • 25
  • 43
4
votes
1 answer

Autokeras exported model performs not as expected

I just installed autokeras on python3.6. After some bug fixing it works well and I can train models with my dataset. After training i get a model with an accuracy of 0.991 and loss of 0.06. With the predict-function it classifies my test dataset…
KaFe
  • 41
  • 3
3
votes
1 answer

Error in implementing autokeras timeseries model

I was trying to implement autokeras TimeSeriesForecaster on a serial dataset. The features and label of the dataset are respectively given below. df1_x = df1_y = 0 2.5 1 2.1 2 2.2 3 2.2 4 1.5 Name: target_carbon_monoxide, dtype:…
Samar Pratap Singh
  • 471
  • 1
  • 10
  • 29
3
votes
2 answers

How to save/load models in AutoKeras 1.0

I'm using AutoKeras 1.0 and I'm having trouble understanding how I'm supposed to save and reload a trained model (plus weights, etc). I can train a model easily, using code similar to: num_data = 500 train_x =…
3
votes
0 answers

Does the Windows Subsystem for Linux (WSL) support cpufreq as used by Python psutil?

I am using the WSL (Ubuntu 18.04.2 LTS) for machine learning projects. So I installed autokeras 1.0 on Python 3.6 which is based on the new tensorflow 2.0. However, all autokeras examples break with the psutil error message "NotImplementedError:…
3
votes
0 answers

Evaluate AutoKeras model gives different results then the same model as pure Keras evaluate (h5 file)

I am using AutoKeras to train my dataset and then save it as AutoKeras file and Keras file(h5). My problem is that evaluating those 2 models gives me different results. This is the code to train the dataset and save the models: if __name__ ==…
user1623454
  • 274
  • 3
  • 14
2
votes
1 answer

tf keras autokeras with early stopping returns empty history

I am trying different models for the same dataset, being autokeras.ImageClassifier one of them. First I go for img_size = (100,120,3) train_dataset = get_dataset(x_train, y_train, img_size[:-1], 128) valid_dataset = get_dataset(x_valid, y_valid,…
Videgain
  • 155
  • 3
  • 15
2
votes
0 answers

Autokeras StructuredDataClassifier InvalidArgumentError: Graph execution error

I'm using Auokeras to choose a model for my dataset. I've tried using StructuredDataRegressor and everything went ok. But now I'm trying to use StructuredDataClassifier and can't get it running: df = edad target F M 13 62 0.75 1.0 0.0 39…
juanmac
  • 121
  • 1
  • 12
2
votes
3 answers

No module named 'keras_tuner'

I'm executing this code on Kaلgle, and install autokeras library on it, !pip install autokeras import matplotlib.pyplot as plt import pandas as pd import datetime %matplotlib inline #Control the default size of figures in this Jupyter…
muhammad
  • 37
  • 2
  • 7
2
votes
1 answer

How to get Reproducible Results with AutoKeras

I need to reproduce results with AutoKeras for the same input and configurations: I tried the following at the beginning of my notebook but still didn't got the same results. I am using Tensorflow 2.0.4 and AutoKeras 1.0.12 seed_value= 0 import…
userInThisWorld
  • 1,361
  • 4
  • 18
  • 35
2
votes
0 answers

Disk limit is reached when using autokeras in GoogleColab

I would like to avoid the error termination when the disk limit is reached when using autokeras in GoogleColab. I am currently using and mounting a 200GB GoogleDrive plan and storing the autokeras training history in the drive to reduce the amount…
2
votes
0 answers

Autokeras consumes all GPU after Trial 1

I faced a problem with autokeras while running an example from the book. The task was to generate architecture for model trained with MNIST dataset ("hello world" difficulty task for autokeras). Also I have an issues using laptop GPU, and I have to…
2
votes
0 answers

Interpretation of AutoKeras Trial Summary Output

For the AutoKeras 1.0 example below: from tensorflow.keras.datasets import mnist import autokeras as ak (x_train, y_train), (x_test, y_test) = mnist.load_data() clf = ak.ImageClassifier(max_trials=10) # It tries 10 different…
cannin
  • 2,735
  • 2
  • 25
  • 32
1
2 3 4