Tagging Categorization Cropping Color Extraction Visual Search Custom Training Custom Model Face Recognition Object Localization Text Recognition Press Media Kit Advertising Blog Careers Commerce and Retail Contacts Hardware IoT Media and Entertainment On-Premise Projects Real Estate Research Publications Team Technology and Cloud

Custom training icon Custom Model Training

Analyze specific visual data by building custom models.

Contact Our Experts

What is Custom Training and How it Works.

Imagga's custom training enables customers to specify the categories to which their content should be assigned and use the Imagga auto-categorization API with the custom-trained model. This is especially useful in the cases where a company has tried to classify content manually but has found it overwhelmingly challenging.

Custom training workflow

The training process is straightforward.

Step one

Dataset

Provide training data (list of non-overlapping categories and sample image data for each category). In case you do not have sufficient data, our data engineering team will advise you on the available options.

Step two

Model training

We build a deep learning classification model trained with your specific categories and data. The existing classified content will be used as a training dataset and after completion, the unclassified content will be automatically processed.

Step three

Deployment

The model is then wrapped in an API so it can be easily plugged in and implemented in your company’s existing systems and workflows.

Benefits of Building Custom Models with Imagga.

Extensive Expertize icon

Extensive Expertise

We have successfully worked with a plethora of companies in various industries, always striving to achieve the best possible results for the image-related business processes of our customers.

Professional Data Collection icon

Professional Data Collection

In case you don't have the image dataset required for quality machine learning we can help and provide a data collection team.

Supreme Computing Power icon

Robust Computing Power

We have the capacity to handle any size of training dataset thanks to our cutting edge internal infrastructure and computation power.

Integration icon

Flexible Deployment

We can operate the running of the technology in our own super-scalable cloud, as well as assists you in deploying it on your premises or integrate it in your applications on the edge.

Need a custom solution? With our expertise we are helping you to go through the whole proccess.

Customer Stories

Plantsnap logo

MEDIA AND ENTERTAINMENT

Training the world’s largest plant recognition model.

There are over 320.000 different species worldwide, meaning that Imagga’s categorizer had to be trained for a huge number of classes. For training, it used over 90 million images, making the scale of this project massive even on an enterprise level.

Read The Full Story

Deploy Your Custom Model
on the Cloud, On-Premises or on the Edge

Cloud icon

Cloud Platform

Use Imagga Image Recognition API on the Cloud to reduce IT costs and to speed up deployment.

On-premise icon

On-Premise Solution

We'll help you deploy Imagga API on your private servers for full compliance with the privacy regulations.

Edge-Mobile icon

Edge/Mobile

You can also export a snapshot of each model to be used directly on the edge.

Have a Question? Check our Frequently Asked Questions.

  • Is there an interface where I can set up a custom training?
    No, currently this is work performed by our expert machine learning team. We are working on a web interface that will make it possible for you to define categories, upload sample photos and do the training yourself. However our team can be of great help for tasks such as defining the categories' structure, running of the training dataset and the training process for achieving optimal results.
  • How many images per category do you need for the training and how big do the images need to be?
    Ideally we need around 1000+ photos per category but 200-500 might work as well if the categories are well distinguishable and each category is well represented by the given photos. The images need to be at least 300px on their shortest side.
  • Is there a limit on the number of categories you can do custom training for?
    Theoretically yes, but in practice you don’t need to worry, we can handle training with tens of thousands of categories.
  • Should each category be represented by the same number of photos?
    The number of photos in each category don't need to be exactly the same, but ideally there won’t be more than x2 times difference between the smallest and largest number of sample photos for their respective categories.
  • Can I use a hierarchy instead of flat structure?
    Our training works with flat structures, so it’s best if you flatten the structure. Of course internally you can have your own knowledge of what hierarchical structure your flattened categories belong to.
  • How long does it take to do the actual training?
    Depending on the complexity of the categories and the number of sample images it might take from a few hours up to 5 business days.
  • Would you use my data for other purposes?
    We are not using your images for any purpose outside of your own project and we don’t share the images in any way. However if you want to contribute to the improvement process of the models, please let us know.
  • What if I am not satisfied with the precision of the results?
    There are several options - adding more diverse sample photos per category can significantly increase the precision rate. Sometimes categories that are overlapping could be the reason for less than optimal results - in certain cases redefining the list of categories would work quite well. In very rare cases we may jointly conclude that we can’t do anything at this stage and you don’t need to pay the success fee. We try to prevent this case by carefully analyzing the definition of the categorization before we start the actual training and request the upfront fee.
Just a moment ...