auto_image_segmentation_with_fine_tuning

The job trains a custom model on a provided dataset that has only one label (with equal number of examples where the label is present and missing). The gradients inside the fine tuned model are used to automatically segment the objects of interest in the image and pixel level segmentation masks are exported for all images wih the label present.

Required Account Privileges: "read"

Request JSON ["inputs"]:

   "augmentation_conditions":
      dict of string to bool
      null allowed 
      Optional. A dict that allows you to control the trasformations applieded to images and videos to increase the dataset size with variations.
      All are true by default, set them to false if they invalidate the data in your use case.
      The options are:
         "horizontal_flip" -  Randomly flips the image/video horizontally.
         "vertical_flip" - Randomly flips the image/video vertically.
         "small_rotation" -  Applies small random rotations up to 30 degrees to the image/video.
         "large_rotation" - Applies larger random rotations up to 90 degrees to the image/video.
         "center_crop" - Crops the image/video around its center keeping aspect ratio and scaled bewteen 0.5 and 1.0 of image size.
         "brightness_jitter" - Randomly adjusts the brightness of the image/video.
         "contrast_jitter" - Randomly adjusts the contrast of the image/video.
         "saturation_jitter" - Randomly adjusts the color saturation of the image/video.
         "blur" - Applies a Gaussian blur to the image/video with a randomly chosen blur radius.
  
   "file_urls":
      list of strings
      null allowed
      An optional list of strings containing the URLs of files to be downloaded.
      
   "download_from_batch_cloud_folder":
      bool
      null NOT allowed
      A boolean indicating whether to download files from the batch cloud folder.

Response JSON ["results"]

   "mask_segmented_image_names_with_download_urls":
      list of lists of strings
         [file_name (string), public_url (string)]

File Requirements

Requires files to be sent via FTP to the cloud batch folder or in the file_urls

Requires the submission of image files and a corresponding JSON file to facilitate model training and object segmentation. 
Only image files are permitted for processing. Ensure that all provided files are in a valid image format (JPG, PNG).
The image dataset must contain an equal number of images where the target label is present and where the target label is missing. This balanced dataset is crucial for effective model training.
examples_with_labels.json:
This JSON file provides a list of the filenames of the images within your submitted image set where the target label is present.