Arctic Watershed Sentinel-2 RGB Images and Labels for Image Segmentation using the Segmentation Zoo program

{

  "TARGET_SIZE": [256,256], # the size of the imagery used to train the model on

  "MODEL": "segformer", # model name

  "NCLASSES": 2, # number of classes

  "BATCH_SIZE": 8, # number of images/labels per batch

  "N_DATA_BANDS": 3, # number of image bands

  "DO_TRAIN": true, # if false, the model will not train, but you will select this config file, data directory, and the program will load the model weights and test the model on the validation subset

  "PATIENCE": 10, # number of epochs of no model improvement before training is aborted

  "MAX_EPOCHS": 100, # maximum number of training epochs

  "VALIDATION_SPLIT": 0.5, #proportion of images to use for validation

  "RAMPUP_EPOCHS": 20, # [Learning Rate-scheduler] rampup to maximim

  "SUSTAIN_EPOCHS": 0.0, # [LR-scheduler] sustain at maximim

  "EXP_DECAY": 0.9, # [LR-scheduler] decay rate

  "START_LR":  1e-7, # [LR-scheduler] starting learning rate

  "MIN_LR": 1e-7, # [LR-scheduler] minimum learning rate. will not go below this rate.

  "MAX_LR": 1e-4, # [LR-scheduler] maximum learning rate. will not exceed this rate.

  "FILTER_VALUE": 0, #if >0, the size of a median filter to apply on outputs (not recommended unless you have noisy outputs)

  "DOPLOT": true, #if true, makes plots

  "ROOT_STRING": "test", #data file (npz) prefix string

  "USEMASK": false, # use the convention 'mask' in label image file names, instead of the preferred 'label'

  "AUG_ROT": 5, # [augmentation] amount of rotation in degrees

   "AUG_ZOOM": 0.05, # [augmentation] amount of zoom as a proportion
  "AUG_WIDTHSHIFT": 0.05, # [augmentation] amount of random width shift as a proportion
  "AUG_HEIGHTSHIFT": 0.05,# [augmentation] amount of random width shift as a proportion
  "AUG_HFLIP": true, #  [augmentation] if true, randomly apply horizontal flips
  "AUG_VFLIP": false, #  [augmentation] if true, randomly apply vertical flips
  "AUG_LOOPS": 10, #[augmentation] number of portions to split the data into (recommended > 2 to save memory)
  "AUG_COPIES": 5  #[augmentation] number iof augmented copies to make
  "SET_GPU": "0" #which GPU to use. If multiple, list separated by a comma, e.g. '0,1,2'. If CPU is requested, use "-1"

 "LOSS_WEIGHTS": false, #if true, apply per-class weights to loss function

 "SET_PCI_BUS_ID": true, #if true, make keras aware of the PCI BUS ID (advanced or nonstandard GPU usage)

 "TESTTIMEAUG": true, #if true, apply test-time augmentation when model in inference mode

 "WRITE_MODELMETADATA": true,# if true, write model metadata per image when model in inference mode

 "OTSU_THRESHOLD": true# if true, and NCLASSES=2 only, use per-image Otsu threshold rather than decision boundary of 0.5 on softmax scores

}

 

 

 

## watersheds_test_run data
Folder containing all the model input data

/modelOut

      | train_data                                                                                                                                                                                                                                                                      |     ├── train_images                                                                                                                                                                                                                                                |     ├── train_labels                                                                                                                                                                                                                                                    |     ├── Train_npzs

      | val_data                                                                                                                                                                                                                                                                      |     ├── val_images                                                                                                                                                                                                                                                    |     ├── val_labels                                                                                                                                                                                                                                                      |     ├── val_npzs

## modelOut
PNG format files containing example model outputs from the train ('_train_' in filename) and validation ('_val_' in filename) subsets as well as an image showing training loss and accuracy curves with `trainhist` in the filename. There are two sets of these files, those associated with the residual unet trained with dice loss contain `resunet` in their name, and those from the UNet are named with `vanilla_unet`.

## weights
There are model weights files associated with each config files.