Questions tagged [automl]

Automated Machine Learning (AutoML) is to make machine learning more accessible by automatically generating a data analysis pipeline that can include data pre-processing, feature selection, and feature engineering methods along with machine learning methods and parameter settings

The goal of Automated Machine Learning (AutoML) is to make machine learning more accessible by automatically generating a data analysis pipeline that can include data pre-processing, feature selection, and feature engineering methods along with machine learning methods and parameter settings that are optimized for your data

More and more research and libraries are available on the topic, examples include auto-sklearn, H2O AutoML and Cloud AutoML.

434 questions
2
votes
0 answers

how to get image from a random point of an uploaded video to feed AutoML model?

I want to be able to run a tensorflow.js model based on image classification but with video. I want to be able to grab multiple snapshots of the video and pass those to the image classification model. How do I grab multiple snapshots of the video…
Zepol
  • 195
  • 2
  • 3
  • 14
2
votes
1 answer

AutoML Pipelines: Label extraction from input data and sampling within Neuraxle or SKLearn Pipelines

I am working on a project that is looking for a lean Python AutoML pipeline implementation. As per project definition, data entering the pipeline is in the format of serialised business objects, e.g. (artificial example): property.json: { "area":…
sim
  • 1,227
  • 14
  • 20
2
votes
1 answer

Python installing old version of matplotlib results in freetype and png error

I am attempting to install the following package: https://pypi.org/project/autocluster/ However, it looks like it requires the use of matplotlib==3.0.3, as when I try to install it i get the following error: I already have newer versions of…
WolVes
  • 1,286
  • 2
  • 19
  • 39
2
votes
1 answer

Cannot get docker image of gcr.io/automl-vision-ondevice/gcloud-container-1.14.0:latest

I got an error when I was trying to download the docker image from gcr.io/automl-vision-ondevice/gcloud-container-1.14.0:latest But I got an error of Access Denied. How can I solve this issue? Thanks a lot. $ export…
2
votes
0 answers

Custom TensorflowJS model (exported from GCP AutoML) not running in HTML deployment

I trained a custom object detection model using Google Cloud AutoML and exported the model as a TensorflowJS package. However, when I try running the model using the HTML deployment example they have here…
2
votes
1 answer

How to inspect the structure of a Google AutoML Tables model?

I have trained a model using Google AutoML Tables. I would like to inspect the general structure of the trained model (which algos were used, what preprocessing if any, etc) In the "Viewing model architecture with Cloud Logging" section of the docs…
3z33etm
  • 1,083
  • 3
  • 15
  • 23
2
votes
1 answer

Node Google Cloud AutoML PredictionServiceClient problem

I'm trying to use the google cloud automl API to use it's classification service but it's returning the following error: { Error: 3 INVALID_ARGUMENT: Request contains an invalid argument. at Object.callErrorFromStatus…
2
votes
1 answer

How can i pass variable to a google cloud function

I am currently creating a cloud task which will import new data to an automl dataset periodically. The target is a GCP cloud function http target. As I don't want to hard code the dataset ID in the cloud function. I want it to accept the dataset id…
2
votes
2 answers

Google AutoML - Possible to authenticate by service account impersonation?

TL;DR - Can I authenticate to AutoML API by impersonating a service account (SA) with my application default credentials (ADC) or must I actually use SA authentication? I would like to be able to authenticate to the AutoML API using ADC when making…
2
votes
1 answer

Neuraxle's RandomSearch() successor

I updated Neuraxle to the latest version (3.4). I noticed the whole auto_ml.py was redone. I checked the documentation but there is nothing about it. On git it seems method RandomSearch() was replaced a long time ago by AutoML() method. However the…
2
votes
0 answers

Importing AutoML edge train model in OpenCV

I trained an object detection model using AutoML Vision which was then exported as a 'saved_model.pb' file. I can load and run this model using the following few lines of code: import tensorflow as tf with tf.Session(graph=tf.Graph()) as sess: …
Dhaval
  • 31
  • 3
2
votes
1 answer

Hyperopt classification task raises error "TypeError: __init__() got an unexpected keyword argument 'n_iter' "

I am trying to use Hyperopt to optimize a classification task on my dataset using Google Colab. However, one of its utilities, cross-validation does not work and raises this error : TypeError: init() got an unexpected keyword argument…
Beg
  • 405
  • 1
  • 5
  • 18
2
votes
2 answers

H2O AutoML leave-one-out performs too much better than 10-folds cross-validation

I have a machine learning problem: 88 instances, 2 classes (40 instances of "FR" class, 48 instances of "RF" class). I tried, by myself, several different algorithms and, evaluating the results with both cross-validation and leave-one-out, I could…
Joseph
  • 23
  • 2
2
votes
0 answers

Google AutoML for time series classification

Google AutoML only supports Image Classification (AutoML vision). While AutoML Tables is for structured data. I need to do time series classification where there is translation invariance in data. AutoML Tables is not an option as it won't handle…
Praveen Kulkarni
  • 2,816
  • 1
  • 23
  • 39
2
votes
1 answer

Error while importing images to Google storage in Cloud AutoML Vision

I am using the google AutoML vision api object detection option in google console.When I try to upload the images to google storage to train the model, I am getting "Failed to import" error. I have tried using the csv file option as well but the…