Give us feedback
Service icon


Stable version 1.0.0 (Compatible with OutSystems 11)
Other versions available for 10
Uploaded on 01 March 2021 by 
 (1 rating)


Connector and sample on how to use Tensorflow to integrate machine learning models into OutSystems applications. Sample uses a pre-trained inception model for image recognition.
Read more

What is TensorFlow?

TensorFlow is an open source library for numerical computation and large-scale machine learning. TensorFlow bundles together a slew of machine learning and deep learning (aka neural networking) models and algorithms and makes them useful by way of a common metaphor. TensorFlow can train and run deep neural networks for handwritten digit classification, image recognition, word embeddings, recurrent neural networks, sequence-to-sequence models for machine translation, natural language processing, and PDE (partial differential equation) based simulations. Best of all, TensorFlow supports production prediction at scale, with the same models used for training.

TensorFlow allows developers to create dataflow graphs—structures that describe how data moves through a graph, or a series of processing nodes. Each node in the graph represents a mathematical operation, and each connection or edge between nodes is a multidimensional data array or tensor.

Inception model?

The inception model is a deep neural network which has already been trained for classifying images into thousands of different categories. This means that by using this model, we can start classifying images immediately without further training.

How does this module work?

- DownloadModel

The DownloadModel action is used to download and apply the inception model from Google ( This is a pre-trained model equivalent do Inception V1.

- Image Recognition

The ImageRecognition receives a record list of Images (structure, binary only) and for each one of them creates a new Tensor, which is then processed and calculated against the pre-trained values.

Please refer to the demo module within this application for additional information.

Release notes (1.0.0)
  • Separate component from the demo
  • Rebuilt the sample as a reactive web app
Reviews (0)