Stack Overflow
Stack Overflow

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
1
vote
1 answer

how to use object detection for bank cheque detail extraction?

I'm working on the project where I need to extract details (cheque no, MICR, branch, a/c no, IFSC) from bank cheques. I decided to use Google AutoML vision object detection for this task but I have the following questions. How to prepare data for…
savan ladani
  • 41
  • 2
  • 5
1
vote
0 answers

cross_val_predict for H2O

I'm looking for equivalent functionality to scikit-learn cross_val_predict function within h2o. I tried to use keep_cross_validation_predictions=True option with autoML, but aml.leader.cross_validation_predictions() returns None. I followed link…
XWen
  • 361
  • 1
  • 2
  • 10
1
vote
1 answer

Create .jsonl files from .csv

I want to use AutoML, specifically the Entity extraction, however, I'm asked to upload a .jsonl file. I don't know that a .jsonl file is nor how to create it. I only have a .csv file. So, how can I create a .jsonl file from a .csv file? And if that…
Andrey Solera
  • 2,311
  • 2
  • 26
  • 51
1
vote
1 answer

Explanation Needed for Autokeras's AutoModel and GraphAutoModel

I understand what AutoKeras ImageClassifier does (https://autokeras.com/image_classifier/) clf = ImageClassifier(verbose=True, augment=False) clf.fit(x_train, y_train, time_limit=12 * 60 * 60) clf.final_fit(x_train, y_train, x_test, y_test,…
Manas shukla
  • 612
  • 5
  • 10
1
vote
1 answer

Can I copy my AutoML models from one project to another?

I have my trained AutoML models in my current GCP project, but I want to copy some of them into another project. Is that possible in GCP, or do I have to create a new AutoML model in my new project with the same dataset and train it again, so I get…
aksonai
  • 101
  • 2
  • 7
1
vote
1 answer

Multiple output classification in Google AutoML Table

Is it possible to train a multiple output classification model using Google AutoML Table? If so, how can I predict a vector and not a scalar of multi-label classes with the AutoML Table? Concatenating the vector of output classes to get a single…
bugfoot
  • 667
  • 7
  • 20
1
vote
1 answer

H2o flow automl temporary sample frame

I have a large frame and used h2o flow run automl with a deep learning algo. However, the training metrics are calculated on a “temporary sample frame”. I could not find any info to this. I am not sure if the automl has been run on the full frame or…
XWen
  • 361
  • 1
  • 2
  • 10
1
vote
1 answer

Problem in accessing h2o models after shutting h2o down

I run h2o automl function using R as described in the help and documentation page (accessed by typing ?h2o.automl). The script is as follows: library(h2o) h2o.init() votes_path <- system.file("extdata", "housevotes.csv", package = "h2o") votes_hf <-…
h45
  • 206
  • 1
  • 6
1
vote
1 answer

H2O MOJO Runtime: Cannot find MOJO implementation backend

I'm trying to run a function on AWS Lambda that loads my H2O MOJO model from S3 and makes a prediction based on function input. My plan is to make a prediction endpoint using API Gateway. However when I call…
brice
  • 1,801
  • 1
  • 10
  • 15
1
vote
1 answer

Glue and For to many models with Automl - R

I want to reproduce this code: X_train_model1 <- data.table::fread("datasets_atualizados/dataset_y1.csv") %>% h2o::as.h2o() X_train_model2<- data.table::fread("datasets_atualizados/dataset_y2.csv") %>% h2o::as.h2o() #Model construction (20…
Guilherme Souza
  • 13
  • 3
1
vote
1 answer

h2o AutoML vs h2o XGBoost - model metrics

I have fairly small dataset: 15 columns, 3500 rows and I am consistenly seeing that xgboost in h2o trains better model than h2o AutoML. I am using H2O 3.26.0.2 and Flow UI. H2O XGBoost finishes in a matter of seconds while AutoML takes as long as it…
anthony
  • 283
  • 1
  • 3
  • 12
1
vote
0 answers

How to i handle a bufferoverflowexception that pops out after using a custom AutoML model?

I am on a tutorial about deploying custom Models on AutoML onto edge, in this case an android device. link is here: https://cloud.google.com/vision/automl/docs/tflite-android-tutorial I followed the step to "customize" it with my own model and run,…
ZeeCeeCee
  • 11
  • 1
1
vote
2 answers

Automating both Uploading the training data label csv and Training processed the model in AutoML Vision Image classification

I have to manually upload the training data label CSV and click on 'train' to train the model. I want to automate all these preferably with python.
Anurag Gupta
  • 41
  • 5
1
vote
0 answers

How do you retrain a Automl model with "new" set of data?

I have a train set of 1000 rows (1 row per day for example). I get a prediction for a set of 5 futures (model.predict). Over the next 5 days, I actually get the data for next 5 days (numbers (sales for example). Now I want the model to be trained on…
Pappu
  • 11
  • 4
1
vote
0 answers

Does google AutoML Vision have batch prediction and how to use it?

First, I got a model trained, which is kinda cool. I am also able - after some headache and confusion about why the model is in us-central - to make single API predictions. I am wondering is it possible to do batch predictions also? Cheers
Fabian Bosler
  • 2,310
  • 2
  • 29
  • 49
1 2 3
…
28 29