Preparing images for training a Object Detection custom object detection model

You can train an Object Detection custom model to detect and label objects within a collection of images. You need upload your training images to IBM Watson Studio and then manually train the model by selecting and identifying the objects in the training images that you want the model to detect in other images.

 

Procedure

  1. Collect images for your classes
  2. [Recommended] Organize your images in .zip files
  3. Upload your files to your project

 

1. Collect images for your classes

For each class you want your model to recognize, collect at least 10 images.

Image file requirements

  • Supported image file formats: JPEG (.jpg) and PNG (.png)
  • Minimum image size: 32 x 32 pixels

Examples

If you don’t have any images yet, you can try out creating a custom model using these sample training images: Sample images.

 

You can upload your training images to Watson Studio one at a time. But you can save time by organizing your images in .zip files and then uploading those .zip files.

.zip file requirements

  • Minimum number of image files: 10
  • Maximum: 10,000 images or 100 MB per .zip file

 

3. Upload your files to your project

From the Assets tab of your project in Watson Studio or from within the Object Detection model builder in Watson Studio, upload your individual image files or .zip files using the data panel. (If the data panel isn’t open, you can open the data panel by clicking the Find and add data icon (The find data icon).)

 

Next steps