Stack Overflow
Stack Overflow

Questions tagged [google-cloud-ml]

Google Cloud ML Engine is a managed service that offers training and/or prediction services using Machine Learning models.

1007 questions
-1
votes
1 answer

Training Custom Model on Vertex AI

I have couple of of questions regarding training custom model: I am using prebuilt Google image and everything is running fine, but I am not able to get the artifacts in "local-package-path" folder. I am using my own container and want to…
Vishwa
  • 14
  • 2
-1
votes
1 answer

Google Cloud ML - Can't Click the Start Training Button

Guys As Google Cloud ML request (AutoML Entity Extraction Project) Each label must have at least 50 annotations. Though ideally, each label should have at least 100 annotations. Fewer annotations often result in inaccurate precision and recall. You…
madbigg
  • 1
-1
votes
2 answers

Difference in Performance between Cloud Compute VM and AI Platform

I have a GCP cloud compute VM, which is an n1-standard-16, with 4 P100 GPUs attached, and a solid state drive for storing data. I'll refer to this as "the VM". I've previously used the VM to train a tensorflow based CNN. I want to move away from…
James
  • 3,957
  • 4
  • 37
  • 82
-1
votes
2 answers

Is there a way to use external, compiled packages for data processing in Google's AI Platform?

I would like to set up a prediction task, but the data preprocessing step requires using tools outside of Python's data science ecosystem, though Python has APIs to work with those tools (e.g. a compiled java NLP tool set). I first thought about…
Chris Ivan
  • 477
  • 5
  • 13
-1
votes
1 answer

How does the google cloud ml engine predict function work?

How does the google cloud ml engine predict function work? Does it apply the same data transformations on the test data point as it does on the training data set?
Prudhvini
  • 55
  • 5
-1
votes
1 answer

Google Cloud ML: I want to recognize Korea license plate

I want to recognize Korea license plate. So, I tried to predicted South Korean license plates using Google Cloud ML. But, Fail to predicted. Google Cloud ML not recognize Korean language part. How do I train to recognize the Korean part? The final…
SANGHOON JEONG
  • 1
-1
votes
1 answer

Single query to get predictions from multiple models in a project present in cloud-ml

I am using the asyncio module in python to query multiple models in a project, in cloud ml to get my predictions. Is there a way to get the predictions from all the models using just one single query. Say I have an image and want the prediction for…
Vishal p
  • 11
  • 2
-1
votes
1 answer

google cloud ML Engine model Version creation and set as default

I want to create Version for ML Engine Model by Rest API and set as default. kindly help me and suggest what is the mistake that I am doing.Sending below request and hitting the post API Below. Trying hitting by Google Auth Playground. Post URL :…
Gaurav Agrawal
  • 1
-1
votes
1 answer

Can anyone help me identify the "bug" in my Google Cloud ML training job?

I was following the link below to replicate the process with new data and new model: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_pets.md Until reach the last step, I activate the training job with the…
Mark Li
  • 429
  • 1
  • 7
  • 21
-1
votes
1 answer

TensorFlow Wide and Deep Model , how many features can I use ?

In this wide and deep model with tensorflow https://www.tensorflow.org/tutorials/wide_and_deep, is there a limit of number of features? I mean is it possible to use 20 columns for training and prediction ? I tried to train my model with 20 columns,…
Sofia
  • 29
  • 5
-1
votes
1 answer

Google Cloud Machine Learning with Decision Tree

We have a Google App Engine application consist of several modules and we are storing our user's data in the Google Cloud DataStore. Now we are going to implement some machine learning algorithms on this data and we are going to use DecisionTree…
tolgatanriverdi
  • 561
  • 9
  • 31
-1
votes
1 answer

Configuration of luminoth training/evaluation job for Google Cloud ML using voc2012

How to configure a luminoth training job (on Google Cloud ML) and tensorboard? I transformed voc2012 to tfrecord format and uploaded to a bucket. So now I want to train the default model (FasterRCNN) using the voc2012 dataset. Which config file…
clic
  • 365
  • 1
  • 13
-1
votes
1 answer

Distributed training of a wide and shallow model

I am working on a very wide and shallow computation graph with a relatively small number of shared parameters on a single machine. I would like to make the graph wider but am running out of memory. My understanding is that, by using Distributed…
savac
  • 300
  • 1
  • 6
-1
votes
2 answers

How do I one-hot encode features using Cloud ML?

How do I one-hot encode features using Cloud ML? Do I have to do this in the TensorFlow model, or can I do it in the Cloud ML SDK itself?
Grace
  • 21
  • 1
-2
votes
2 answers

Model not training properly accuracy is constant while training a rgb image dataset

I am training a model on fruits360 dataset from kaggle. I have 0 dense layers, and 3 convolutional layers in my keras model. My input shape is (60,60,3) as the images are loaded in rgb format. please help me to troubleshoot what is the problem…
yash rathod
  • 1
  • 1
1 2 3
…
67
68