Knowledge Center

Search Results

Home Getting started Tutorials

Deploy an operational AI model Predict California house prices Classifying images of clothes Predicting mood from raw audio data Gene expression prediction Classifying car damages Skin lesion segmentation

Documentation

Projects view

Create a new project Navigate to a project

Recent experiments overview

Recent experiments menu

Search and filter for projects

Share your filters

Datasets view

Import files and data sources to the Platform

Requirements on imported datasets Data formats supported by the Peltarion Platform Csv file specifications Npy file specifications Zip file specifications How to import a file or a data source Combining data types into one dataset

Edit an imported dataset for use in experiments

Dataset features

Feature set

Feature encoding

Standardization Min-max normalization None Categorical

Subset of a dataset

Create a subset

Feature distribution

Understanding the feature distribution Subset statistics

Working with multiple dataset versions

Naming of dataset versions How to check subset settings of a saved dataset version How to edit a dataset version Create a new version of a dataset

Search and filter for datasets Datasets used in tutorials

Calihouse dataset Fashion MNIST dataset MNIST dataset Tagger dataset

Modeling view

Build an AI model

Create an experiment Add a block or a snippet to an experiment

Snippets - your gateway to deep neural network architectures

Choosing the right snippet Going further

DenseNet snippet

DenseNet architecture How to use the DenseNet snippet Reference

Tiramisu snippet

Tiramisu snippet architecture How to use the Tiramisu snippet Reference

U-net snippet

U-net architecture How to use the U-net snippet Reference

VGG snippet

VGG architecture How to use the VGG without weights snippet Reference

Inception snippet

Inception architecture How to use the Inception snippet References

ResNetv2 snippet

ResNetv2 architecture How to use the ResNet snippet References

CNN snippet

CNN snippet architecture

CNN + FC snippet

CNN + FC snippet architecture

Pretrained snippets

Transfer learning with pretrained snippets Available pretrained snippets

How to use pretrained snippets

First experiment Second experiment Catastrophic forgetting Why set weights trainable to No

VGG - pretrained

VGG architecture How to use the VGG with weights snippet Reference

Blocks

Input Target Dense Activation Scaling Dropout Batch normalization 2D Convolution block 2D Deconvolution block 2D Max pooling block 2D Average pooling 2D Global average pooling 2D Upsampling 2D Zero padding Flatten Concatenate Add Reshape Embedding

Image augmentation

Image augmentation settings How to augment images in a dataset

Activations

ReLU Sigmoid Softmax Tanh Hard sigmoid Linear

Loss functions

Binary crossentropy

When to use binary crossentropy

Categorical crossentropy

When to use categorical crossentropy

Mean absolute error

Why use mean absolute error When to use mean absolute error

Mean squared logarithmic error

Why use Mean squared logarithmic error When to use Mean squared logarithmic error

Mean squared error

Why use mean squared error When to use mean squared error

Poisson

When to use Poisson loss function Further reading

Squared hinge

When to use Square hinge

Run a model

Before running a model The Run settings section The Run button

Optimizers and compiler options

Ball rolling in an artificial landscape Gradient descent Batch size Learning rate Momentum

What optimizer to bring to a deserted island

Optimizer test with Rosenbrock function How optimizers behave at a saddle point

Experiment states

Created state Queued state Running state Paused state Completed state Failed state Dequeued state

Improve your model

Change run settings Change block parameters

Working with multiple experiments

How to duplicate experiment Link to parent experiment

Copy blocks with weights to another model

Multiple inputs Transfer learning Trainable or non-trainable Copy with weights parameters

How to copy blocks with weights

Download and deploy model with weights

h5 limitations

Search and filter for experiments

Share your filters

Experiment tagging

How to edit an experiment’s tags How to use tags in the experiment search

Modeling canvas controls

Controls to navigate the Modeling canvas Tools macOS keyboard shortcuts Windows/Linux keyboard shortcuts

Information pop-up

Troubleshooting

Evaluation view

Classification loss metrics

Loss curve Accuracy AUC — Area under curve Gradient norm Precision Recall Averaging of metrics for multi-class classification models

Regression loss metrics

MAE — mean absolute error MAPE — mean absolute percentage error MSE — mean squared error

Model evaluation

Confusion matrix Error distribution curve Prediction scatterplot

Navigating the loss curve and metrics diagram

Checkpoints — best and last epoch X-axis labels Y-axis labels Keyboard shortcuts

Search and filter for experiments

Share your filters

Experiment tagging

How to edit an experiment’s tags How to use tags in the experiment search

Deployment view

Enable deployment for requests Batching Token validity

Using the API with Curl

Test curl method with a deployed MNIST model Deployment parameters

Access authentication

Basic access authentication Bearer access authentication

Using the API in Python

Image classification Tabular data Images and tabular data Image to image Numpy to numpy

Test the deployment from a Python script

Python script example with deployed mnist model

Access authentication

Basic access authentication Bearer access authentication

Deploy to API limitations

Unsupported deployment scenarios Request size Latency Input data

Download API spec

Interpreting the API output

Regression problem Classification problem Responses to batch requests Error responses from the API

Search and filter deployed experiments

Share your filters

Organization settings view

Access Organization settings view

Members view

Add and remove members of the organization Platform roles Possible account membership status in the organization How to remove a team member How to change the role of a team member How to invite a team member How to resend a team member invitation How to withdraw a new team member invitation

My profile view

Reset password Leave organization

Quota view

Organization resources How to manage quotas

End of organization quota plan

Cheat sheets

Multi-label image classification / cheat sheet

Problem formulation Data preparation Modeling

Single-label image classification / cheat sheet

Problem formulation Data preparation Modeling

Image segmentation / mark a single object type within an image / cheat sheet

Problem formulation Data preparation Modeling Evaluation

Glossary Product updates

March 20 - Updates March 11 - Updates February 11 - Updates January 29 - Updates January 15 - Updates November 27 - Updates November 15 - Updates October 30 - Updates September 18 - Updates August 31 - Updates August 09 - Updates July 26 - Updates

Terms

Dataset licenses

Calihouse Cifar-10 Fashion-MNIST MNIST Tagger Deep learning yeast UTRs Skin lesion segmentation

Snippets with weights licenses

How do I report a bug?How do I reset my password?How do I upgrade my usage plan?Where do I ask for help?What do I do when my quota plan has reached the limit?Technical requirements

Documentation / Modeling view / Modeling canvas controls

Modeling canvas controls

Controls to navigate the Modeling canvas

Zoom to fit

Zoom to fit
This will expand the model to fit the whole Modeling canvas.

Zoom to 100%

Zoom to 100%
Click this icon to zoom into the center of the part of the model that is shown in the Modeling canvas.

Zoom out

Zoom in

Zooming example

Figure 1. Modeling canvas controls

Tools

Delete selection

Auto layout

Expand all groups

Collapse all groups

Undo

Redo

macOS keyboard shortcuts

Pan around canvas

Copy selected blocks

Paste copied blocks

Multi-select

Select all

Delete selected blocks

Undo

Redo

Windows/Linux keyboard shortcuts

Pan around canvas

Copy selected blocks

Paste copied blocks

Multi-select

Select all

Delete selected blocks

Undo

Redo